doc-tdd-fixer

Pass

Audited by Gen Agent Trust Hub on Aug 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to use local shell commands for managing a review saga and tracking execution time. These operations (mkdir, date, cat) are benign and used purely for metadata management and enforcing internal timeouts.
  • Evidence: Shell command blocks in SKILL.md for directory creation and timestamp calculation.
  • [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because its core functionality requires reading and acting upon external audit reports and persona reviews.
  • Ingestion points: Reads from .aidoc/audit/07_TDD-audit.md and .aidoc/review/ artifacts.
  • Boundary markers: The skill does not define explicit delimiters for ingested report content.
  • Capability inventory: The skill can write to the filesystem (TDD edits, backups, fix reports) and dispatch subagents based on report content.
  • Sanitization: No specific sanitization or validation of the audit findings is described before the agent applies patches or dispatches agents.
  • Context: As the primary purpose of this skill is automated remediation, the intake of these files is necessary for its operation.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 1, 2026, 08:55 PM
Security Audit — agent-trust-hub — doc-tdd-fixer