skills/steipete/clawdis/summarize/Gen Agent Trust Hub

summarize

Pass

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill configuration specifies the installation of a CLI tool via a Homebrew tap ('steipete/tap/summarize'). This is a resource managed by the skill's author.
  • [COMMAND_EXECUTION]: The skill's primary functionality relies on executing the 'summarize' command-line binary to process files and network resources.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from external sources.
  • Ingestion points: URLs, YouTube video transcripts, and local PDF/text files (SKILL.md).
  • Boundary markers: Absent. The instructions do not define delimiters or provide guidance to the agent to ignore instructions embedded within the processed content.
  • Capability inventory: The 'summarize' tool can access the local file system and perform network requests to fetch content.
  • Sanitization: Absent. No explicit validation or escaping of the ingested content is defined in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
May 19, 2026, 08:10 AM
Security Audit — agent-trust-hub — summarize