quality-audit
Pass
Audited by Gen Agent Trust Hub on Apr 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local shell commands including unilyze, jq, git, and dotnet to perform static analysis and manage report files.
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it reads and processes untrusted project source code.
- Ingestion points: Source files identified for review in SKILL.md Phase 2.
- Boundary markers: Absent; no delimiters are used when reading file content.
- Capability inventory: Includes shell command execution (unilyze, jq, git) and file system access.
- Sanitization: Absent; the content is analyzed as-is.
Audit Metadata