skills/hashintel/brunch/ln-review/Gen Agent Trust Hub

ln-review

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection (Category 8) due to its core function of processing external data.
  • Ingestion points: The skill reads files from the local codebase specified in the arguments, as well as 'memory/SPEC.md' and 'memory/PLAN.md'.
  • Boundary markers: The skill does not employ explicit delimiters or instructions to prevent the agent from following directions potentially embedded within the analyzed code.
  • Capability inventory: The skill's instructions are limited to read operations and cognitive analysis; it does not contain commands for network access, file writing, or shell execution.
  • Sanitization: No sanitization, escaping, or validation of the content within the analyzed files is performed prior to processing.
  • [SAFE]: The skill includes attribution links to external GitHub repositories (mattpocock/skills and theswerd/aicode) for documentation purposes; these are well-known community resources and do not involve runtime code execution or downloads.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 08:47 PM
Security Audit — agent-trust-hub — ln-review