apply-cv-reviewer
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze user-provided CVs and supporting materials which are external, untrusted data sources.
- Ingestion points: The workflow in
SKILL.md(Step 1) explicitly prompts for the user's target role, CV, and supporting documents such as project writeups, papers, and transcripts. - Boundary markers: The skill uses a highly structured output format (Sections 1-8) and defines four distinct analytical registers (observation, interpretation, assumption, recommendation) which help provide context, though they do not programmatically sanitize input.
- Capability inventory: The skill is limited to diagnostic text output and bullet point rewriting within the agent's response. It does not perform network write operations, file system modifications, or shell command executions.
- Sanitization: There is no explicit requirement for the agent to sanitize or escape the content of the CV before processing it, though the analytical workflow encourages decomposing data into fixed buckets.
- [SAFE]: The skill references several external resources from trusted academic institutions and career services (Oxford, Harvard, MIT, Yale, Berkeley, and Purdue) to establish CV conventions. These references are used for documentation purposes and are consistent with the skill's primary function.
Audit Metadata