The Agent Skills Directory

[SAFE]: The skill is strictly limited to read-only operations on project artifacts. No patterns of data exfiltration, malicious command execution, or unauthorized file modification were detected.
[PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it ingests untrusted data from project files.
Ingestion points: Ingests content from spec.md, plan.md, tasks.md, and constitution.md during the load phase.
Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the processing logic.
Capability inventory: The skill contains no instructions for subprocess execution, file writing, or network operations, effectively mitigating the risk of injection exploitation.
Sanitization: No input validation or sanitization steps are defined for the documentation content.

analyze