competitive-ads-extractor
Pass
Audited by Gen Agent Trust Hub on Mar 16, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill is documentation-only and contains no associated scripts or executable components.
- [PROMPT_INJECTION]: The skill establishes a workflow for ingesting and analyzing untrusted content from external sources (Facebook and LinkedIn), which creates a potential surface for indirect prompt injection. * Ingestion points: Competitor advertisements and messaging from external web platforms. * Boundary markers: The skill includes high-level usage tips but lacks technical delimiters or instructions for the agent to isolate external commands. * Capability inventory: The agent is instructed to write files to the local directory
~/competitor-ads/. * Sanitization: No logic is provided to validate or filter the content retrieved from external sources.
Audit Metadata