porters-five-forces
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill includes a bundled Python utility,
five_forces_scorer.py, which the agent is instructed to run to generate industry reports. This script uses standard libraries and operates locally on provided JSON data without making external network connections. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external industry data, creating a potential surface for indirect prompt injection.
- Ingestion points: Untrusted data is ingested from
forces.jsonduring the scoring workflow. - Boundary markers: The process uses structured JSON as a data format which provides some structural separation, but does not include explicit delimiters to prevent the agent from following instructions embedded in the data.
- Capability inventory: The skill includes file system read access for the input JSON and stdout/file write access for the resulting report.
- Sanitization: The skill performs JSON schema validation via the Python script but does not sanitize the string content for potential malicious instructions.
Audit Metadata