shortlink-qr

Pass

Audited by Gen Agent Trust Hub on Oct 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by ingesting untrusted data and using it to modify configuration files.
  • Ingestion points: The skill accepts slug, url, and title parameters from user input or external requests.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the processing logic described.
  • Capability inventory: The skill has the capability to write to local files (_redirects, .svx), execute git commands (commit, fetch, reset, push), and modify the macOS clipboard.
  • Sanitization: There is no evidence of sanitization or validation of the url or title fields before they are written to the redirect configuration or the Brain resource file.
  • [COMMAND_EXECUTION]: The skill performs automated shell-level operations, including executing git commands and interacting with the portless and pi-notes tools. It uses a specific bot identity shitratgit[bot] for commits.
  • [DATA_EXPOSURE]: The skill operates on a hardcoded absolute file path targeting a specific user's home directory: /Users/joel/Code/joelhooks/joel-dev-link-shortener/_redirects. While appropriate for a personal skill by the author, absolute paths to user directories can be a security concern if utilized in broader contexts.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 9, 2026, 11:45 AM