competitive-ads-extractor
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external ad copy and creative content from platforms like Facebook and LinkedIn, which represents an indirect prompt injection attack surface.
- Ingestion points: External ad libraries (Facebook Ad Library, LinkedIn) as described in SKILL.md.
- Boundary markers: The instructions do not define clear delimiters or specify that the agent should ignore instructions embedded within the ad data.
- Capability inventory: The skill performs file system writes to the user's home directory (~/competitor-ads/) and implies the use of web scraping/browsing tools.
- Sanitization: There are no instructions for sanitizing or escaping the content retrieved from external sources before it is processed by the agent.
Audit Metadata