bewerbungsexperte
Pass
Audited by Gen Agent Trust Hub on Nov 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external, potentially untrusted data that could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: The tool
cv_generator.pyingests data from SQLite database tables (specificallyassistant_user_profileandcontacts) and scans local directory and file names. - Boundary markers: The generated ASCII CV output uses basic text headers but lacks explicit delimiters or instructions to the LLM to ignore embedded commands within the career data.
- Capability inventory: The skill possesses the ability to execute local scripts and use their output to generate further content, such as cover letters or LinkedIn profile optimizations.
- Sanitization: No sanitization, validation, or filtering of instructions is performed on the text retrieved from the database or the filesystem metadata.
Audit Metadata