skills/tacoda/tack/tack-constrain/Gen Agent Trust Hub

tack-constrain

Pass

Audited by Gen Agent Trust Hub on Nov 22, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: A detailed analysis of the skill's instructions, metadata, and scripts revealed no evidence of malicious patterns such as prompt injection, credential theft, or unauthorized data exfiltration. The skill follows security best practices for repository management.\n- [COMMAND_EXECUTION]: The skill includes shell scripts (scripts/scaffold.sh and templates/check-context.sh) that perform local file operations to set up repository structure and verify documentation accuracy. These scripts use standard system utilities (e.g., grep, cp, chmod) and operate exclusively within the target project directory.\n- [INDIRECT_PROMPT_INJECTION]: The skill establishes a documentation framework (AGENTS.md) for AI agents. It mitigates the risk of agents being misled by stale or inaccurate information by providing automated drift checks that verify documentation against the actual source code identifiers and paths.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 22, 2026, 01:30 AM