support-access-analyzer
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a boilerplate for a command-line utility. It performs standard file reading and writing operations based on user-provided arguments.
- [INDIRECT_PROMPT_INJECTION]: The skill's design includes an ingestion surface for external data, which is a potential vector for indirect prompt injection.
- Ingestion points: The script
run.pyreads content from a file path specified by the--inputflag. - Boundary markers: No delimiters or specific safety instructions are provided to the agent regarding the input content.
- Capability inventory: The
run.pyscript possesses file system read and write capabilities. - Sanitization: The script performs structural validation by parsing the input as JSON but does not sanitize the values within the data.
Audit Metadata