ai-job-scout
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources which could contain malicious instructions designed to influence the agent. Ingestion points:
SKILL.md(Step 1: candidate profile; Step 2: job listings; Step 3: company product/about pages). Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when processing or re-presenting external content. Capability inventory: The skill generates text and HTML reports, including writing to a local.htmlfile (references/interactive-report.md). Sanitization: No sanitization, escaping, or filtering of external content is mentioned before interpolation into reports. - [DYNAMIC_EXECUTION]: The skill generates interactive HTML content that includes JavaScript based on external data. Pattern:
references/interactive-report.mdinstructs the agent to produce a self-contained.htmlfile with inline CSS and JavaScript. Risk: External data from job listings or profiles could contain malicious scripts that would be executed if the user opens the generated report, or could attempt to influence the agent's subsequent actions.
Audit Metadata