skills/tkersey/dotfiles/plan/Gen Agent Trust Hub

plan

Pass

Audited by Gen Agent Trust Hub on Mar 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues detected during the analysis of the skill instructions or the associated validation script.
  • [PROMPT_INJECTION]: The skill instructions do not contain any malicious patterns. It explicitly includes an 'External-input trust gate' which instructs the agent to treat instructions embedded in imported documents as untrusted context, providing a defense against indirect prompt injection.
  • [COMMAND_EXECUTION]: The skill references a local Python script (plan_contract_lint.py) used for validating the output format. This script is included in the skill package and was found to be benign, performing only text processing and regex-based validation of the plan's structure.
  • [DATA_EXFILTRATION]: The skill instructions explicitly forbid mutating repository-tracked files while in 'Plan Mode' and do not contain any patterns for unauthorized network access or data transfer.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 17, 2026, 08:48 PM
Security Audit — agent-trust-hub — plan