test-fix-verify
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute standard development shell commands, including 'pnpm test', 'pytest', 'go test', 'pnpm build', and 'cargo build'. These are necessary for the skill's primary function of verifying code changes.
- [EXTERNAL_DOWNLOADS]: The skill uses 'pnpm install' to manage dependencies. This targets official package registries and is a routine operation for software development assistants.
- [PROMPT_INJECTION]: The skill processes untrusted data (local code changes and Git diffs), which presents a surface for indirect prompt injection.
- Ingestion points: File changes and descriptions are read via 'git diff' and 'git status' as specified in 'SKILL.md'.
- Boundary markers: No explicit markers are used to separate untrusted code content from the agent's internal logic.
- Capability inventory: The skill has permissions to execute shell commands ('pnpm', 'pytest', 'cargo', 'go') and interact with a browser using Chrome MCP tools ('chrome_navigate', 'chrome_screenshot') as documented in 'SKILL.md'.
- Sanitization: No sanitization or filtering of ingested code content is described.
Audit Metadata