competitive-ads-extractor
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to scrape and analyze ad copy from external sources like Facebook and LinkedIn. This ingested content is controlled by third parties and could contain instructions intended to influence the agent's behavior.
- Ingestion points: External ad libraries and competitor websites.
- Boundary markers: The instructions do not define delimiters or warnings to ignore embedded instructions in the scraped data.
- Capability inventory: The skill records screenshots and writes analysis files to the user's home directory.
- Sanitization: No mechanisms for filtering or sanitizing the scraped ad copy are mentioned.
- [NO_CODE]: The skill consists entirely of markdown documentation and usage examples. It does not include any accompanying scripts (Python, JavaScript, or Shell), significantly reducing the risk of direct malicious code execution or obfuscated logic.
Audit Metadata