seo-geo-factdensity
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes untrusted data from web pages, which could potentially contain hidden instructions designed to influence the agent's behavior. Ingestion points: PageSnapshot (rendered_dom, raw_html) as defined in SKILL.md. Boundary markers: None present to distinguish untrusted content from internal instructions. Capability inventory: Tools include Read, Grep, Glob, WebFetch, and Bash. Sanitization: No sanitization or validation logic is defined for the external content.
- [COMMAND_EXECUTION]: The verification instructions describe a command-line pattern for running a script with a URL argument, which may be vulnerable to injection if the agent does not sanitize the input. Evidence: 'node scripts/factdensity.mjs --url ' found in SKILL.md.
Audit Metadata