competitive-ads-extractor
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill functions by scraping and analyzing content from external ad libraries (Facebook, LinkedIn, etc.), which represents an attack surface for indirect prompt injection. Maliciously crafted ad copy could attempt to influence the agent's analysis or override instructions during the processing phase.
- Ingestion points: External content from ad libraries such as Facebook and LinkedIn is brought into the agent context for extraction and analysis (SKILL.md).
- Boundary markers: There are no explicit delimiters or instructions provided to the agent to disregard embedded commands within the scraped ad data.
- Capability inventory: The skill demonstrates the capability to perform network operations for scraping and file system writes to save screenshots and reports in
~/competitor-ads/(SKILL.md). - Sanitization: The instructions do not specify any filtering, sanitization, or validation of the retrieved ad copy before it is analyzed by the language model.
Audit Metadata