sdlc-apply
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from external markdown files (intent.md, spec.md) which could potentially contain malicious instructions.
- Ingestion points: The skill reads intent.md and spec.md files to generate implementation plans.
- Boundary markers: No explicit delimiters or boundary markers are used when reading these files.
- Capability inventory: The skill performs shell command execution (python3), file system writes, and git operations.
- Sanitization: No specific sanitization or filtering of external content is mentioned.
- [COMMAND_EXECUTION]: The skill performs shell command execution as part of its normal operation.
- It executes scripts/fingerprint.py to calculate digests for artifacts.
- It interacts with the git CLI for branch and worktree management.
- It runs project-specific tests as defined in the plan.
- These operations are necessary for the skill's purpose and are conducted within an approved planning framework.
Audit Metadata