ops-forecast-analyzer
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from an external file, creating a surface where malicious instructions could be embedded in the input data to influence the agent.
- Ingestion points: The
run.pyscript reads data from a file path provided via the--inputcommand-line argument usingpathlib.Path.read_text(). - Boundary markers: There are no boundary markers or instructions defined in
SKILL.mdto help the agent distinguish between data and potential instructions within the input. - Capability inventory: The skill possesses the capability to read and write files on the local file system (
pathlib.Path.read_textandpathlib.Path.write_text). - Sanitization: The input data is loaded as JSON but is not subjected to schema validation or sanitization before being processed by the skill logic.
Audit Metadata