career-changer-cv
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data, such as job advertisements and career inventory files, to generate resume content. This creates an indirect prompt injection surface where malicious instructions in a job description could potentially influence the agent's output.
- Ingestion points: The skill explicitly requests external data like "two or three real job ads" and a
career-inventoryfile inSKILL.md. - Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are used when processing these inputs.
- Capability inventory: The skill is restricted to text generation; it performs no subprocess calls, file writing, or network operations.
- Sanitization: There is no evidence of input validation or filtering for the external content provided by the user.
Audit Metadata