schematic
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands such as 'git log' and 'git diff' to retrieve branch information and file contents. These operations are standard for the skill's stated goal of reverse-engineering project specifications.
- [INDIRECT_PROMPT_INJECTION]: The skill processes arbitrary data from git branches, which represents an attack surface for indirect prompt injection if the code files contain malicious instructions.
- Ingestion points: Phase 2 (Parallel Deep Exploration) and Phase 3 (Cross-Check for Gaps) read file contents and diffs into the agent's context.
- Boundary markers: The instructions do not define specific delimiters or security prompts to prevent the agent from following instructions embedded within the analyzed code.
- Capability inventory: The skill can execute local shell commands via the git CLI and create new documentation files within the repository.
- Sanitization: There is no evidence of content sanitization or instruction filtering before the code content is processed by the exploration agents.
Audit Metadata