api-reference-creator
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external documentation sources which could contain malicious instructions.\n
- Ingestion points: The skill triggers on API-related requests and uses
ReadandGreptools to access project files (SKILL.md).\n - Capability inventory: The skill is granted
Bash(cmd:*),Write, andEditpermissions, allowing for significant system-level interaction and file modifications (SKILL.md).\n - Boundary markers:
SKILL.mddoes not define delimiters or specific instructions to ignore or isolate embedded commands within the documentation data it processes.\n - Sanitization: No input validation or content filtering is implemented for external data before it is handled by the agent's executable tools.\n- [NO_CODE]: The skill consists only of documentation and instructions in
SKILL.mdwithout any accompanying scripts or executable code files.
Audit Metadata