find-bugs
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses local CLI tools including
gitandgh(GitHub CLI) to gather branch diffs and repository configuration. These commands are executed to provide the necessary data for the code review and are consistent with the skill's functional description. - [EXTERNAL_DOWNLOADS]: The skill's metadata references a source URL within the
getsentry(Sentry) organization on GitHub. As Sentry is a well-known service provider, this reference is documented as a trusted source. - [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it processes code changes which may contain untrusted data.
- Ingestion points: Reads branch diffs and individual file contents through git and local filesystem access (Phase 1).
- Boundary markers: There are no explicit delimiters defined to separate the ingested code from the analysis instructions.
- Capability inventory: Capabilities are limited to read operations and local CLI interaction via git and gh. No file-writing or network exfiltration capabilities are present.
- Sanitization: The skill does not perform sanitization on the code content it reviews. However, since this is its primary function and no dangerous capabilities are exposed, the risk is mitigated.
- [SAFE]: No obfuscation, hardcoded credentials, persistence mechanisms, or unauthorized privilege escalation attempts were found in the skill logic or metadata.
Audit Metadata