skills/yashas-30/nyx/conductor-revert/Gen Agent Trust Hub

conductor-revert

Warn

Audited by Gen Agent Trust Hub on Jun 23, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The instructions direct the agent to execute shell commands using variables sourced from user arguments or local files (e.g., git log --grep="{trackId}"). The lack of explicit sanitization or escaping instructions for these variables creates a risk of command injection if a track ID or task identifier contains shell metacharacters like semicolons or pipes.
  • [PROMPT_INJECTION]: The skill exhibits a vulnerability surface for indirect prompt injection by processing external data files to drive its logic.
  • Ingestion points: The skill reads data from conductor/tracks.md and plan.md (SKILL.md).
  • Boundary markers: No delimiters or "ignore embedded instructions" warnings are used when the agent processes the content of these files.
  • Capability inventory: Across the instructions, the skill is granted the ability to run git log, git revert, and perform file-write operations to plan.md and metadata.json (SKILL.md).
  • Sanitization: There is no evidence of validation or filtering for the data ingested from the track or plan files before it is used to determine commit SHAs or update project status.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 23, 2026, 01:08 AM
Security Audit — agent-trust-hub — conductor-revert