hr-officer-pro
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process resumes and candidate information which are untrusted external inputs. Ingestion points: Resumes and candidate details are processed during the 'Resume Scoring Matrix' and 'Interview Script' steps as defined in
SKILL.md. Boundary markers: The instructions do not specify any delimiters or safety prompts to ensure the agent distinguishes between the task instructions and potentially malicious commands embedded in the resumes. Capability inventory: The skill is capable of writing the generated recruitment packages to local Markdown files. It does not possess network access or the ability to execute system commands. Sanitization: No mechanisms for sanitizing or filtering input data are present in the provided instructions or templates.
Audit Metadata