skills/ferueda/harness/implement-plan/Gen Agent Trust Hub

implement-plan

Pass

Audited by Gen Agent Trust Hub on Jun 26, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted data from the codebase which could contain malicious instructions. Although this is the primary function of the skill, it represents an indirect injection surface.\n
  • Ingestion points: The skill reads plans from 'dev/plans/' and auxiliary instructions from directories like 'skills/', '.cursor/skills/', or '.claude/skills/' (SKILL.md).\n
  • Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within these external files.\n
  • Capability inventory: The agent is authorized to write code to the local filesystem and execute shell commands via make ('make check', 'make test', 'make fix').\n
  • Sanitization: No sanitization or validation of the plan's content is performed before execution.\n- [COMMAND_EXECUTION]: The skill executes shell commands for verification.\n
  • Evidence: Instructs the agent to run 'make check', 'make test', and 'make fix' within the codebase environment. (SKILL.md)
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 26, 2026, 10:13 PM
Security Audit — agent-trust-hub — implement-plan