security-review
Pass
Audited by Gen Agent Trust Hub on Mar 23, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted codebase data.
- Ingestion points: Reads local codebase files including package.json, source code, and configuration files as specified in PHASES 1 through 6.
- Boundary markers: Absent; there are no instructions to wrap or delimit the analyzed file content to prevent it from being interpreted as instructions.
- Capability inventory: Filesystem read access, report generation, and the ability to append execution metadata to local telemetry files (~/.claude/projects/skill-telemetry.md).
- Sanitization: Absent; the skill does not implement validation or escaping of the ingested code content.
- [DATA_EXPOSURE]: The skill instructions direct the agent to access and analyze sensitive files such as .env, credentials, and private keys. This behavior is strictly aligned with the skill's primary purpose of performing security audits and does not involve external data exfiltration.
- [COMMAND_EXECUTION]: The skill includes a telemetry phase that writes execution metadata to the local filesystem (~/.claude/projects/skill-telemetry.md). This is intended for performance tracking and iterative improvement of the skill's auditing capabilities.
Audit Metadata