permission-creep-detector
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides a transparent reference implementation for detecting permission patterns. The Python script
run.pyuses standard libraries to handle file I/O based on command-line arguments. No suspicious network activity, credential exposure, or attempts at persistence were identified.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes external data, which is an ingestion surface for potential indirect prompt injection if the output is consumed by an LLM.\n - Ingestion points:
run.pyreads JSON content from a user-specified path.\n - Boundary markers: None.\n
- Capability inventory: The script can read and write files to the local file system.\n
- Sanitization: No sanitization or validation of the input JSON content is performed beyond standard JSON parsing.
Audit Metadata