freehire-search

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill retrieves job descriptions from the freehire.me public API and displays them to the agent. This represents an indirect prompt injection surface where external, third-party content could contain malicious instructions designed to override agent behavior.
  • Ingestion points: The agent context receives data from the /api/v1/agent/jobs/search and /api/v1/jobs/{slug} endpoints, processed in cli/src/commands/search.ts and cli/src/commands/detail.ts.
  • Boundary markers: No explicit delimiters or instructions are provided to the agent to treat fetched job descriptions as untrusted or to ignore instructions within them.
  • Capability inventory: The skill relies on Bash to execute its CLI tool within the agent environment.
  • Sanitization: The cleanHtml utility in cli/src/helpers.ts handles HTML stripping and entity decoding for display, but does not provide security-focused filtering against prompt injection techniques.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 07:20 PM
Security Audit — agent-trust-hub — freehire-search