Which Tool

AdvisoryAudited by Static analysis on May 12, 2026.

Overview

No suspicious patterns detected.

Findings (0)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

NoteHigh Confidence

ASI09: Human-Agent Trust Exploitation

What this means

A user or agent may try documented flags such as --json or -a and get failures or incorrect automation assumptions.

Why it was flagged

The documentation advertises options and multi-command behavior, while the included scripts/which.py only parses one positional argument and calls shutil.which(args.cmd). This is a low-impact reliability/documentation mismatch rather than evidence of malicious behavior.

Skill content

Options:
  -a, --all          Show all matching paths, not just the first
  -s, --silent       Exit silently ...
  --json             Output as JSON array

Recommendation

Treat this as a simple single-command path lookup unless the implementation is updated to match the documented options.