spec-driven-archive

Pass

Audited by Gen Agent Trust Hub on Mar 26, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses node {{SKILL_DIR}}/scripts/spec-driven.js to perform administrative tasks such as listing changes, checking task completion status, and moving directories to an archive. This is standard automation for development-oriented skills.
  • [DATA_EXPOSURE]: The skill interacts with files in the .spec-driven/ directory at the project root. It reads delta specifications and writes updates to main specification files. This activity is confined to documentation management within the project workspace.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes content from delta spec files which could potentially contain malicious instructions if the project files are untrusted.
  • Ingestion points: Content is read from markdown files in .spec-driven/changes/<name>/specs/ during the merging process (SKILL.md).
  • Boundary markers: The skill does not use specific delimiters or ignore-instructions to isolate the merged content from the rest of the project specifications.
  • Capability inventory: The skill has the capability to write to the local filesystem and execute Node.js scripts.
  • Sanitization: There is no evidence of content sanitization or validation of the requirement blocks being merged into the main spec files.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 26, 2026, 02:18 PM