The Agent Skills Directory

[SAFE]: No malicious behavior, data exfiltration, or obfuscation patterns were detected. The skill's operations are consistent with its primary purpose of providing implementation plan validation and codebase analysis.
[COMMAND_EXECUTION]: The skill utilizes standard shell utilities and version control commands to perform codebase analysis and verification.
Evidence: The validation workflow and supporting reference materials (references/dry-principles.md, references/gap-analysis-guide.md) include the use of grep, find, ls, and git log to discover existing patterns and components. It also references test execution using frameworks like npm test, jest, vitest, and pytest during the TDD validation phase.
[PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it processes untrusted data from user-provided implementation plans.
Ingestion points: The workflow in SKILL.md (Step 1) involves loading and analyzing implementation plan files provided by the user.
Boundary markers: The instructions do not define specific delimiters or "ignore previous instructions" warnings when processing the contents of the ingested plan files.
Capability inventory: The skill has access to codebase reading tools (grep, ls), file modification capabilities (SKILL.md Step 8), and the ability to recommend/run test commands.
Sanitization: No explicit sanitization or validation of the plan file content is performed prior to analysis.

validate-plan