partner-dependency-analyzer
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes structured input (JSON/CSV) which could contain malicious instructions designed to influence the agent's behavior during data analysis.
- Ingestion points: The
run.pyscript reads the content of a file provided via the--inputcommand-line argument usingPath.read_text(). - Boundary markers: There are no explicit boundary markers or instructions to the agent to ignore embedded commands within the processed data.
- Capability inventory: The script possesses file system capabilities, including directory creation (
mkdir), file reading (read_text), and file writing (write_text). - Sanitization: The script parses JSON using the standard library, but does not implement validation, sanitization, or schema enforcement for the content of the data being processed.
Audit Metadata