The Agent Skills Directory

[SAFE]: The skill performs directory listings and metadata extraction from project-specific documentation folders (docs/adrs, docs/prds, docs/prps). It does not attempt to access sensitive system files, environment variables, or credentials.
[COMMAND_EXECUTION]: Uses standard Linux utilities such as grep, sed, head, printf, and ls to parse markdown content. These operations are restricted to the local filesystem and are consistent with the skill's stated documentation auditing purpose.
[DATA_EXPOSURE]: No data exfiltration patterns or network operations were detected. The skill only processes local file metadata for the purpose of generating an index table for the user.
[INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests and processes content from untrusted documentation files.
Ingestion points: Reads from docs/prds/*.md and docs/prps/*.md (SKILL.md).
Boundary markers: Absent.
Capability inventory: Includes file reading and shell-based string manipulation (grep, sed).
Sanitization: Absent; the skill extracts lines matching specific patterns (title:, status:, etc.) directly into formatted output.

blueprint-docs-list