cv-content-generator
Pass
Audited by Gen Agent Trust Hub on Feb 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes local shell commands via npm run to perform data analysis and search operations, specifically search:evidence, analyze:jd, and check:coverage.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests untrusted data from external job descriptions.
- Ingestion points: Job descriptions are read from source-data/jd-{company}.txt and unstructured data from content/knowledge/raw/.
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present when processing external text.
- Capability inventory: The agent can execute local npm scripts and write generated markdown or YAML content to various directories in the content/ folder.
- Sanitization: There is no evidence of sanitization or validation performed on the input text from job descriptions before it is used for analysis or content generation.
Audit Metadata