skills/tbsten/mir/mir-update-snippet/Gen Agent Trust Hub

mir-update-snippet

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses npx mir commands to interact with a snippet management tool, performing tasks such as retrieving snippet metadata, syncing variables, and executing installation tests.
  • [PROMPT_INJECTION]: There is a risk of indirect prompt injection as the skill processes and tests snippets that may contain untrusted data or malicious instructions.
  • Ingestion points: Snippet content is ingested into the agent context via the npx mir info command in SKILL.md.
  • Boundary markers: No specific boundary markers or delimiters are defined to isolate untrusted snippet content from the agent's operational instructions.
  • Capability inventory: The skill is capable of executing shell commands and performing file system operations, specifically writing to the /tmp directory.
  • Sanitization: The skill relies on a manual checklist for path traversal detection but does not implement automated sanitization or sandboxed execution for snippet hooks during the installation test step.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 08:25 PM