release-docs

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION] (SAFE): The skill uses standard shell commands (ls, wc, cat, grep, jq) for inventory and validation purposes. All commands are used in a read-only or local verification capacity consistent with the skill's purpose.
  • [DATA_ACCESS] (SAFE): The skill accesses local project files in the plugins/compound-engineering/ directory to extract metadata. No sensitive system paths or credentials are accessed.
  • [INDIRECT_PROMPT_INJECTION] (LOW): The skill ingests content from external files to generate documentation summaries.
  • Ingestion points: Agent, command, skill, and MCP server files located within the project subdirectories.
  • Boundary markers: Absent; the skill directly processes the content of these files.
  • Capability inventory: The skill can read/write local files and execute basic shell utilities for text processing and count verification.
  • Sanitization: The skill includes a check to skip files with invalid frontmatter, providing a basic level of validation.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 04:10 PM