openclaw-secret-scanning-maintainer
Pass
Audited by Gen Agent Trust Hub on May 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The script
scripts/secret-scanning.mjsuses the GitHub CLI (gh) to perform administrative actions such as deleting comments and redacting bodies. These operations are performed using secure execution methods (spawnSync) to prevent shell injection. - [PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks because it processes untrusted user content from GitHub. A mandatory evidence chain is identified: (1) Ingestion points: Content is downloaded via the
fetch-contentcommand inscripts/secret-scanning.mjsinto temporary files; (2) Boundary markers: No explicit delimiters are used inSKILL.mdwhen the agent reads the downloaded content; (3) Capability inventory:scripts/secret-scanning.mjsallows administrative actions like comment deletion and alert resolution; (4) Sanitization: No specific filtering is applied to the ingested content before processing.
Audit Metadata