alterlab-pra-copywriter
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection attack surface by processing untrusted external data.\n- Ingestion points: The agent is instructed to read local project files and perform web searches to gather context (SKILL.md).\n- Boundary markers: The instructions lack clear delimiters or safety warnings to ignore instructions embedded within the ingested data.\n- Capability inventory: The skill can write multiple markdown files to the local project directory and use web search tools.\n- Sanitization: There is no evidence of input validation or sanitization before processing the external files or search results.
Audit Metadata