ClawHub
Back to skill

Security audit

Positioning Truth Tracer

Security checks for vulnerabilities and agentic risk

Overview

The skill’s workflow is coherent, but its manifest understates persistent writes, local helper use, and optional external connector access.

Install only if you are comfortable granting this skill permission to write project memory, propose registry events through the local helper, update hot-cache/open-loop records after approval, and optionally use configured search/scrape connectors. Do not rely on the lite manifest alone as a complete permission description.

A.I.G

Vulnerability Patterns
  • 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
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
distribution-manifest.json:2
Finding

Declared Capabilities Understate Persistent Write, Script Execution, and Network Retrieval Behavior

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (1)

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 · SKILL.md (reported line 68)May include surrounding context.

md
## Save Results

After delivering the truth set, ask: "Save these results for future sessions?" On confirmation, save to `memory/narrative/positioning-truth-tracer/YYYY-MM-DD-<topic>.md` — see [skill-contract.md §Save Results Template](../../../references/skill-contract.md). Unverified or comparative differentiators go only to `memory/events/claims.ndjson` via an authorized `operation: propose` request to `registry-events.py`; a durable positioning statement worth canonizing goes only to `memory/events/narrative.ndjson` via an authorized `operation: propose` request to `registry-events.py` (only [narrative-registry](../../../protocol/narrative-registry/SKILL.md) writes canonical `memory/narrative-registry/` files); a stage/date fact goes only to `memory/events/launches.ndjson` via an authorized `operation: propose` request to `registry-events.py`. Do not write memory without asking.

## Reference Materials

Static analysis

No suspicious patterns detected.