The Agent Skills Directory

[COMMAND_EXECUTION]: Uses Bash to run ls, fd, awk, and grep for file discovery and text parsing within the docs/adrs/ directory. These are standard operations for generating documentation indices.
[PROMPT_INJECTION]: Analyzes local ADR files to extract titles and statuses, which creates a surface for indirect prompt injection if the project files contain malicious instructions.
Ingestion points: Documentation files in docs/adrs/*.md are ingested in SKILL.md.
Boundary markers: Absent; the skill does not explicitly instruct the agent to ignore instructions embedded in the ADR files.
Capability inventory: Includes Bash commands for file system access and text processing as defined in SKILL.md.
Sanitization: Not present; the skill extracts and displays content as-is from the source files.
[SAFE]: No remote downloads, network exfiltration, or hardcoded credentials were found. The skill operates exclusively on local project documentation.

blueprint-adr-list