market-intelligence-gather
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data by scraping competitor advertisements from platforms like Facebook Ad Library and LinkedIn.
- Ingestion points: External ad platforms (Facebook Ad Library, LinkedIn) are accessed to extract ad copy and metadata, which are then processed by the agent.
- Boundary markers: The skill documentation does not specify the use of clear delimiters or instructions for the agent to ignore embedded commands within the scraped content.
- Capability inventory: The skill performs network operations to fetch ads and writes results to the local filesystem (e.g.,
~/competitor-ads/). - Sanitization: No explicit sanitization or filtering of the scraped content is described in the skill instructions, making it vulnerable to malicious instructions hidden in ad copy.
Audit Metadata