skills/jeremylongshore/tons-of-skills-marketplace/detecting-exposed-secrets-files/Gen Agent Trust Hub
detecting-exposed-secrets-files
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external web servers which may contain malicious instructions designed to influence the agent when it processes the scan results.
- Ingestion points: The safe_get function in scripts/probe_secrets.py retrieves the response body from target URLs.
- Boundary markers (absent): The scan report does not use clear boundary markers or instructions to the agent to treat the retrieved content as untrusted data.
- Capability inventory: The skill has the ability to execute network requests and write results to the filesystem via command-line arguments.
- Sanitization (absent): The retrieved content is compared against regex patterns but is not otherwise sanitized before being included in the report evidence.
- [EXTERNAL_DOWNLOADS]: The skill performs network requests to target URLs provided by the user to check for exposed files.
- [COMMAND_EXECUTION]: The skill executes a local Python script (probe_secrets.py) to perform its scanning logic.
Audit Metadata