ClawHub
Back to skill

Security audit

grounded

Security checks for vulnerabilities and agentic risk

Overview

This skill gives disclosed, proportionate guidance for checking repository references and does not show hidden data access or unsafe automatic behavior.

Install this if you want an agent to verify repository references using the grounded tool. Review the optional init-agent commands before running them, especially the global skills install target and any non-dry-run fix command, because those are the paths that can write files.

A.I.G

Vulnerability Patterns
  • 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
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
85% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · references/commands.md (reported line 37)May include surrounding context.

md
scanning). Terminal output is for humans; parse JSON instead.
* `stale-doc-ref` is opt-in: `--enable stale-doc-ref`. Never assume it
  ran; default scans exclude it.
* `init-agent --skill` installs this skill to `~/.claude/skills/grounded`
  (all projects); `--skill-project` installs to `.claude/skills/grounded`
  (this repo only). Bare `init-agent` never writes outside the repo.

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
85% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · references/commands.md (reported line 38)May include surrounding context.

md
* `stale-doc-ref` is opt-in: `--enable stale-doc-ref`. Never assume it
  ran; default scans exclude it.
* `init-agent --skill` installs this skill to `~/.claude/skills/grounded`
  (all projects); `--skill-project` installs to `.claude/skills/grounded`
  (this repo only). Bare `init-agent` never writes outside the repo.