T08 · Insecure Dependencies
Warning
- Location
SKILL.md:58- Finding
Untrusted Skill Metadata Can Trigger Unsafe Global Package Installation
- Content
View full analysis
- Remediation
View remediation
Security audit
Skill Dependency Fixer
Security checks for vulnerabilities and agentic risk
Overview
This skill has a legitimate dependency-repair purpose, but it can lead agents to install global packages or an unverified binary without enough safeguards.
Review this skill before installing. Use dry-run first, inspect every proposed package, avoid running fixes with elevated privileges, and prefer pinned or verified installation methods over the direct latest-release binary. Install only dependencies declared by skills you trust.
Vulnerability Patterns
- Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
- Insecure DependenciesIntroduces malicious components through unsafe dependency sources
- 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
- Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (2)
T03 · Remote Payload Retrieval and Execution
Note
- Location
SKILL.md:118- Finding
Mutable Release Binary Is Downloaded Without Integrity Verification
- Content
View full analysis
- Remediation
View remediation
' "$HOME/bin/skill-dep-fixer" | sha256sum -c - chmod +x "$HOME/bin/skill-dep-fixer" ``` 4. Prefer cryptographically signed release artifacts and verify signatures against a documented, trusted public key. 5. Publish build provenance or attestations and provide reproducible-build instructions where feasible. 6. Ensure that checksum or signature verification failure stops installation before `chmod` or execution. 7. Avoid instructing users to execute mutable release artifacts that cannot be independently authenticated. ]]>
Vulnerability Patterns
- Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
- 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 (3)
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The trigger phrases include broad, natural-language prompts like "skills are broken" and "openclaw doctor," which can match ordinary troubleshooting requests and cause this skill to activate unexpectedly. Because the skill's purpose is to generate or recommend package installation and repair actions, accidental invocation can lead to unreviewed system-modifying guidance or follow-on actions.
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
The skill describes scanning and auto-fixing dependencies but does not prominently warn that fixes may install global npm packages, pip packages, Homebrew formulae, or otherwise alter the local environment. Users may treat the skill as diagnostic-only and be surprised by system modifications, especially since the document includes direct installation commands and update guidance.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
The invocation list repeats ambiguous triggers without requiring clear user intent or confirmation, increasing the chance that routine support language activates the skill. In this context, unintended activation is more dangerous because the skill is designed around detecting missing packages and optionally fixing them, which normalizes potentially invasive system changes.
- Content
Static analysis
No suspicious patterns detected.