incu-way-docs
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill reads external files including source code, README.md, and documentation files to generate its output. If these files contain malicious instructions disguised as comments or documentation, they could influence the agent's behavior. The skill lacks explicit instructions to sanitize or isolate this input from its reasoning process.
- Ingestion points: Codebase files (source code, README.md, docs/, PRD.md) specified in Phase 0.
- Boundary markers: Absent; the skill does not instruct the agent to ignore instructions embedded within the codebase content.
- Capability inventory: File system read access, file system write access (to docs/ directory), and git command execution.
- Sanitization: Absent; no sanitization or validation of the ingested codebase content is specified before processing.
- [COMMAND_EXECUTION]: The skill executes local git commands to manage documentation branches and worktrees. These commands are triggered based on user confirmation and are restricted to the local repository context.
- Evidence: Use of
git switch,git pull,git worktree, andgit fetchin the 'Isolation setup' section of SKILL.md.
Audit Metadata