competitive-ads-extractor
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to scrape and analyze ad copy and creatives from external sources like the Facebook Ad Library and LinkedIn. Because these sources are controlled by third parties, they can contain malicious instructions intended to override the agent's behavior.
- Ingestion points: External ad copy, headlines, and metadata retrieved from ad libraries (SKILL.md).
- Boundary markers: Absent. The skill does not provide instructions to treat the ingested ad content as data rather than instructions, nor does it define clear delimiters.
- Capability inventory: The skill writes analysis reports and saves screenshots to the local file system (e.g.,
~/competitor-ads/) (SKILL.md). - Sanitization: None. The skill does not implement or recommend sanitization of the scraped text before the LLM processes it for identifying 'problems' or 'value propositions'.
Audit Metadata