Back to skill

Security audit

Chronos

Security checks for vulnerabilities and agentic risk

Overview

Chronos appears intended to provide local time-awareness, but it installs broad persistent agent hooks and has a path-handling flaw that could overwrite user files if abused.

Review the hook entries before installing, prefer project scope or dry-run where available, and avoid unpinned quick-install commands in sensitive environments. Expect local ~/.chronos ledger/state files containing tool timing metadata. The session_id path validation issue should be fixed before using the full hook stack on machines where hook input or plugin context could be influenced by untrusted projects or tooling.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Findings (2)

T09 · Insecure Skill Coding Practices

Error
Location
scripts/_lib.sh:49
Finding

Unvalidated Session Identifier Enables Path Traversal and Arbitrary File Overwrite

Content
View full analysis
/dev/null || true) if [ -z "${sid:-}" ]; then local file="$CHRONOS_HOME/current-session" if [ -f "$file" ]; then sid=$(cat "$file") else sid="anon-$(now_epoch)" echo "$sid" > "$file" fi fi echo "$sid" } ``` ```bash # scripts/session_start.sh:9-32 INPUT=$(cat) SESSION=$(resolve_session_id "$INPUT") LEDGER=$(ledger_path "$SESSION") STATE=$(state_path "$SESSION") NOW_UTC=$(now_utc_iso) NOW_LOCAL=$(now_local_iso) NOW_EPOCH=$(now_epoch) TZ=$(tz_name) OFFSET=$(utc_offset) # Init ledger (truncate if fresh session start) : > "$LEDGER" # Init state if command -v jq >/dev/null 2>&1; then jq -n \ --arg s "$SESSION" --arg iso "$NOW_UTC" --arg loc "$NOW_LOCAL" \ --arg tz "$TZ" --arg off "$OFFSET" --argjson ep "$NOW_EPOCH" \ '{session_id:$s, started_at_utc:$iso, started_at_local:$loc, started_at_epoch:$ep, tz:$tz, utc_offset:$off, turn:0, last_user_at_utc:$iso, last_user_at_epoch:$ep}' \ > "$STATE" else cat > "$STATE" <
Remediation
View remediation
.jsonl`. - Store the original identifier only inside the state file if needed. 3. Enforce canonical-path containment: - Resolve both `CHRONOS_HOME` and the destination path to canonical absolute paths. - Verify that the destination begins with the canonical home path plus the platform path separator. - Abort without writing if containment fails. 4. Apply identical protections in: - `scripts/_lib.sh` - `scripts/_lib.ps1` - `installers/opencode/plugin.ts` 5. Harden file creation: - Create `CHRONOS_HOME` with user-only permissions. - Create ledger and state files with restrictive permissions. - Avoid following symbolic links where platform APIs permit it. - Use exclusive or no-follow file-opening flags for security-sensitive writes. 6. Add regression tests for identifiers containing: - `../` and `..\` - Absolute Unix paths - Windows drive and UNC paths - Encoded separators - Newlines and control characters - Excessively long values ]]>

T08 · Insecure Dependencies

Warning
Location
README.md:11
Finding

Unpinned Third-Party Package Execution in Installation Instructions

Content
View full analysis
Remediation
View remediation
add OthmanAdi/chronos --skill chronos -g ``` 2. Pin the Chronos npm package: ```bash pi install npm:chronos-skill@1.0.0 ``` 3. Publish cryptographic integrity information: - Provide the npm integrity digest for the reviewed package. - Publish signed checksums for release archives. - Use signed Git tags or attestations for releases. 4. Prefer a repository-local installation path from a fixed release: ```bash git clone --branch v1.0.0 --depth 1 https://github.com/OthmanAdi/chronos.git cd chronos git verify-tag v1.0.0 ./installers/claude-code/install.sh ``` 5. Clearly document the trust boundary: - Explain that `npx` downloads and executes registry-hosted code. - Identify the expected package publisher and exact version. - Recommend reviewing the resolved package before execution in sensitive environments. 6. Use lockfiles and automated dependency scanning for any future runtime or installer dependencies. ]]>
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Rogue AgentSelf-Modification, Session Persistence
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Findings (45)

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The declared description is about runtime behavior of a skill that provides temporal awareness to agents. The supplied code chunk does not implement temporal reasoning, ledger logic, recency checks, cooldown rules, or any decision-making behavior related to time. Instead, it is an installer/uninstaller script for Claude Code that edits local configuration, manages hook registration, and copies files into skill directories. Those actions are materially different from the declared primary purpose and introduce undeclared capabilities around filesystem/configuration modification. While installation is related to deploying the skill, this code chunk itself does not match the described functional behavior of the skill.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The declared description presents a runtime agent skill for temporal reasoning and time-based decision support. The supplied code does not implement any temporal ledger, recency logic, cooldown handling, retry windows, memory staleness checks, or agent-triggered decision rules. Instead, it is purely an installation/setup utility that inspects the execution environment, chooses bash vs PowerShell, and emits corresponding configuration exports. That is a materially different primary purpose from the declared description, so this is a clear mismatch.

Content

No source excerpt is available for this finding.

Agent Config Directory Access

High
Category
Agent Snooping
Confidence
95% confidence
Finding

This installer is explicitly designed to modify Claude Code's settings and inject hook configuration into the agent's trusted config directory. Even though this appears to be the intended functionality of the skill, writing hook commands into ~/.claude/settings.json grants persistent code-execution influence over the agent environment, which is security-sensitive because a compromised or trojanized skill installer could establish durable execution paths without additional review.

Content

Scanner excerpt · installers/claude-code/install.sh (reported line 3)May include surrounding context.

sh
#!/usr/bin/env bash
# chronos — Claude Code installer
# Concatenates chronos hooks into ~/.claude/settings.json (or .claude/settings.json with --project).
# Uses array concat per hook event so existing hooks (mempalace, planning-with-files, etc.) are preserved.

set -euo pipefail

Agent Config Directory Access

High
Category
Agent Snooping
Confidence
97% confidence
Finding

At this location the script creates and targets either project-local .claude/settings.json or the user-wide $HOME/.claude/settings.json, then later populates it with hook entries and copies executable scripts. This is dangerous because project or user agent configuration is a high-trust execution surface; modifying it can persistently alter agent behavior across future sessions and repositories, and project-local installation can also introduce repo-scoped hook execution that other users may inherit.

Content

Scanner excerpt · installers/claude-code/install.sh (reported line 40)May include surrounding context.

sh
if [ "$SCOPE" = project ]; then
    mkdir -p .claude; TARGET=.claude/settings.json
  else
    mkdir -p "$HOME/.claude"; TARGET="$HOME/.claude/settings.json"
  fi
fi

Agent Config Directory Access

High
Category
Agent Snooping
Confidence
90% confidence
Finding

Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.

Content

Scanner excerpt · CONTRIBUTING.md (reported line 26)May include surrounding context.

md
{
  "_comment": "chronos — drop these entries into ~/.claude/settings.json or .claude/settings.json. Replace ${CHRONOS_ROOT} with the absolute path to your chronos checkout, e.g. /c/Users/you/Documents/here-now-projects/chronos. On Windows with Git Bash, .sh paths work. For pure PowerShell, use the .ps1 variants below and set shell to powershell.",
  "hooks": {
    "SessionStart": [
      {

Agent Config Directory Access

High
Category
Agent Snooping
Confidence
90% confidence
Finding

Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.

Content

Scanner excerpt · README.md (reported line 124)May include surrounding context.

md
{
  "_comment": "chronos — drop these entries into ~/.claude/settings.json or .claude/settings.json. Replace ${CHRONOS_ROOT} with the absolute path to your chronos checkout, e.g. /c/Users/you/Documents/here-now-projects/chronos. On Windows with Git Bash, .sh paths work. For pure PowerShell, use the .ps1 variants below and set shell to powershell.",
  "hooks": {
    "SessionStart": [
      {

Agent Config Directory Access

High
Category
Agent Snooping
Confidence
90% confidence
Finding

Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.

Content

Scanner excerpt · installers/claude-code/settings.json (reported line 2)May include surrounding context.

json
{
  "_comment": "chronos — drop these entries into ~/.claude/settings.json or .claude/settings.json. Replace ${CHRONOS_ROOT} with the absolute path to your chronos checkout, e.g. /c/Users/you/Documents/here-now-projects/chronos. On Windows with Git Bash, .sh paths work. For pure PowerShell, use the .ps1 variants below and set shell to powershell.",
  "hooks": {
    "SessionStart": [
      {

Agent Config Directory Access

High
Category
Agent Snooping
Confidence
90% confidence
Finding

Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.

Content

Scanner excerpt · README.md (reported line 138)May include surrounding context.

md
{
  "_comment": "chronos — Codex CLI hooks. Drop into ~/.codex/hooks.json (user) or <repo>/.codex/hooks.json. Also add [features] codex_hooks = true to ~/.codex/config.toml. Replace ${CHRONOS_ROOT}. Note: Codex PreToolUse matches Bash only; Read/Write/Edit tool events may be unavailable until coverage extends.",
  "hooks": {
    "SessionStart": [
      { "command": "bash ${CHRONOS_ROOT}/scripts/session_start.sh" }

Agent Config Directory Access

High
Category
Agent Snooping
Confidence
90% confidence
Finding

Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.

Content

Scanner excerpt · installers/codex/config.toml.fragment (reported line 2)May include surrounding context.

text
{
  "_comment": "chronos — Codex CLI hooks. Drop into ~/.codex/hooks.json (user) or <repo>/.codex/hooks.json. Also add [features] codex_hooks = true to ~/.codex/config.toml. Replace ${CHRONOS_ROOT}. Note: Codex PreToolUse matches Bash only; Read/Write/Edit tool events may be unavailable until coverage extends.",
  "hooks": {
    "SessionStart": [
      { "command": "bash ${CHRONOS_ROOT}/scripts/session_start.sh" }

Agent Config Directory Access

High
Category
Agent Snooping
Confidence
90% confidence
Finding

Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.

Content

Scanner excerpt · installers/codex/hooks.json (reported line 2)May include surrounding context.

json
{
  "_comment": "chronos — Codex CLI hooks. Drop into ~/.codex/hooks.json (user) or <repo>/.codex/hooks.json. Also add [features] codex_hooks = true to ~/.codex/config.toml. Replace ${CHRONOS_ROOT}. Note: Codex PreToolUse matches Bash only; Read/Write/Edit tool events may be unavailable until coverage extends.",
  "hooks": {
    "SessionStart": [
      { "command": "bash ${CHRONOS_ROOT}/scripts/session_start.sh" }

Agent Config Directory Access

High
Category
Agent Snooping
Confidence
90% confidence
Finding

Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.

Content

Scanner excerpt · installers/codex/install.sh (reported line 39)May include surrounding context.

sh
mv "$TMP" "$TARGET"

# Enable feature flag
CONF="$HOME/.codex/config.toml"
[ -f "$CONF" ] || touch "$CONF"
if ! grep -q '^\s*codex_hooks\s*=\s*true' "$CONF" 2>/dev/null; then
  if ! grep -q '^\[features\]' "$CONF" 2>/dev/null; then

Lp1

High
Category
MCP Least Privilege
Confidence
75% confidence
Finding

The skill uses 'env' capability that is not listed in its permissions. This may indicate deceptive intent or missing permission declarations.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · CONTRIBUTING.md (reported line 7)May include surrounding context.

md
To add chronos support for a new agent platform:

1. Create `installers/<platform>/README.md` describing the platform's hook or plugin API
2. Write the context injection: SessionStart must emit `now_utc`, `now_local`, `tz`, `ledger`, `state`, `session`
3. Write per-turn injection: UserPromptSubmit must emit `turn`, `session_duration`, `since_last_user`
4. Write the ledger writer: PreToolUse appends `started_at`, PostToolUse appends `finished_at + duration_ms + success`

Rp1

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · README.md (reported line 23)May include surrounding context.

md
## The problem

LLMs do not know what time it is. They guess. They report "just now" when it was two hours ago. They retry failed commands without checking that the last attempt was 10 seconds ago. They run silently in autonomous loops with no idle detection.

[Arxiv 2510.23853](https://arxiv.org/abs/2510.23853) measured this empirically: even frontier models with timestamps injected into context reach only **65% temporal reasoning alignment** with human judgment. Timestamps appear in fewer than 4% of reasoning traces. The ceiling exists because having access to timestamps is not enough. Agents need explicit rules for *when to look at the clock*.

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · README.md (reported line 143)May include surrounding context.

OpenCode

bash
mkdir -p ~/.config/opencode/plugins
cp installers/opencode/plugin.ts ~/.config/opencode/plugins/chronos.ts
mkdir -p ~/.config/opencode/skills/chronos
cp SKILL.md ~/.config/opencode/skills/chronos/SKILL.md

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

Declaring the skill 'required for autonomous or long-running agents' without clear boundaries encourages unconditional activation and over-reliance on this skill across broad workflows. In practice, that can bias agent behavior toward persistent ledger inspection and tool use even when temporal reasoning is unnecessary, expanding attack surface and increasing the chance of unintended data access or interference with other skills.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
85% confidence
Finding

Declaring the skill 'required for autonomous or long-running agents' without clear boundaries encourages unconditional activation and over-reliance on this skill across broad workflows. In practice, that can bias agent behavior toward persistent ledger inspection and tool use even when temporal reasoning is unnecessary, expanding attack surface and increasing the chance of unintended data access or interference with other skills.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · installers/adal/README.md (reported line 9)May include surrounding context.

bash
# path may vary by ADAL version — check docs
mkdir -p ~/.adal/skills/chronos
cp SKILL.md ~/.adal/skills/chronos/SKILL.md
cp AGENTS.md ~/.adal/skills/chronos/AGENTS.md

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

All lifecycle hooks use an empty matcher, so they trigger for every session, prompt, and tool event. That broad scope increases attack surface and makes any behavior in the referenced scripts run universally, including in contexts where the user may not expect prompt- or tool-driven shell execution.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

This configuration executes shell commands automatically on SessionStart, UserPromptSubmit, PreToolUse, PostToolUse, and Stop, but the file itself provides no user-facing warning about the frequency and sensitivity of those executions. Because these hooks run around prompts and tool activity, they can observe or influence sensitive workflows and normalize hidden command execution inside the agent lifecycle.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

All hook matchers are empty, so the configured commands run for every session start, prompt submission, tool invocation, and stop event without any scoping. In this skill, that means multiple PowerShell scripts are automatically executed across the full agent lifecycle, increasing attack surface and making any unsafe behavior in those scripts trigger universally rather than only in narrowly intended contexts.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · installers/cursor/README.md (reported line 8)May include surrounding context.

Install (project)

bash
mkdir -p .cursor/rules
cp .cursor/rules/chronos.mdc .cursor/rules/chronos.mdc

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · installers/hermes/README.md (reported line 8)May include surrounding context.

Install

bash
mkdir -p ~/.hermes/skills/chronos
cp SKILL.md ~/.hermes/skills/chronos/SKILL.md

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · installers/openclaw/README.md (reported line 8)May include surrounding context.

Install

bash
mkdir -p skills/chronos
cp SKILL.md skills/chronos/SKILL.md
cp AGENTS.md skills/chronos/AGENTS.md