civil-service-application
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data (job advertisements and career history) to generate formatted application responses.\n
- Ingestion points: The 'Required Inputs' section in
SKILL.mdspecifies the job advert and the person's career examples as necessary inputs.\n - Boundary markers: The instructions do not define specific delimiters or safety warnings to ignore potentially malicious instructions that might be embedded within provided job advertisements.\n
- Capability inventory: The skill does not invoke specific file system or network tools; its capabilities are limited to text generation within the agent's default language modeling environment.\n
- Sanitization: There are no instructions for sanitizing or validating the external content before it is interpolated into the agent's processing logic.\n- [NO_CODE]: The skill consists entirely of markdown documentation and instructions for the AI agent, with no executable scripts, binaries, or source code files included.
Audit Metadata