spec-driven-resync-code-mapping

Pass

Audited by Gen Agent Trust Hub on Apr 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands using node to run a local auditing script (scripts/spec-driven.js) and ls for directory verification. Arguments for these commands are derived from user-provided paths and repository metadata.
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by ingesting and interpreting potentially untrusted data from project files to automate mapping repairs.
  • Ingestion points: Specification files (e.g., .spec-driven/specs/INDEX.md), implementation files, and test files found throughout the repository (SKILL.md).
  • Boundary markers: Absent; the instructions do not specify the use of delimiters or provide directives for the agent to ignore instructions embedded within the analyzed content.
  • Capability inventory: The skill can execute Node.js scripts (specifically scripts/spec-driven.js) and perform file system writes to update specification frontmatter (SKILL.md).
  • Sanitization: Absent; the instructions do not describe any validation or sanitization for the content read from the repository before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 12, 2026, 01:19 PM
Security Audit — agent-trust-hub — spec-driven-resync-code-mapping