prepare-inspection-readiness
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection because it is designed to ingest and analyze external documentation such as previous inspection reports, audit findings, and industry warning letters which could contain hidden malicious instructions.
- Ingestion points: Data enters the agent context through the required 'Previous inspection reports', 'Industry warning letters', and 'audit findings' inputs defined in the Inputs and Procedure sections.
- Boundary markers: While the procedure uses structured templates and markdown headers to organize output, there are no explicit instructions or delimiters provided to the agent to ignore or isolate potentially embedded commands within the ingested text.
- Capability inventory: The skill is granted powerful capabilities including 'Bash', 'Write', 'Edit', 'Read', and 'Grep' tools, which could be misused if a prompt injection attack is successful.
- Sanitization: The skill contains no logic for filtering, escaping, or validating the content of provided GxP documents before they are processed by the agent.
Audit Metadata