skills/nicknisi/ideation/express/Gen Agent Trust Hub

express

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests external data from the local environment via the git status --porcelain command. If a repository contains files with maliciously crafted names, these could theoretically be interpreted as instructions by the agent.
  • Ingestion points: The skill executes git status --porcelain within SKILL.md to check for uncommitted changes.
  • Capability inventory: The skill is authorized to use powerful tools including Bash, Write, Edit, and Agent, creating a capability surface for potential exploitation if the agent is influenced by the command output.
  • Boundary markers: The instructions do not specify any markers or negative constraints to ensure the agent ignores content within the git command's output.
  • Sanitization: The skill lacks logic to sanitize or validate the output of the git command before the agent acts upon the repository state.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 10:01 PM
Security Audit — agent-trust-hub — express