press-release-writer
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided announcement data and has access to file-system tools. \n
- Ingestion points: The announcement argument hint in SKILL.md serves as the entry point for untrusted data. \n
- Boundary markers: The instructions do not define delimiters or provide warnings to ignore instructions embedded within the user input. \n
- Capability inventory: The skill is configured with allowed-tools Read and Write in SKILL.md. \n
- Sanitization: There is no evidence of input validation or sanitization to prevent adversarial instructions from influencing the agent's behavior.
Audit Metadata