nodejs-expert
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface (Category 8).\n
- Ingestion points: The skill is designed to ingest and process user-provided code for review tasks as described in the identity and examples sections of SKILL.md.\n
- Boundary markers: There are no explicit instructions or delimiters defined to isolate untrusted user input from the agent's core instructions.\n
- Capability inventory: The skill utilizes high-privilege tools including
Bash,Write,Edit,Read, andGlobwhich are active during its operation.\n - Sanitization: No input sanitization, filtering, or validation steps are included to mitigate the risk of instructions embedded within user code being obeyed by the agent.\n- [PROMPT_INJECTION]: The metadata contains deceptive and unverifiable claims (Category 7), specifically the 'verified: true' flag and a future-dated 'lastVerifiedAt' timestamp, which may mislead users regarding the skill's actual security status.
Audit Metadata