summarize

Pass

Audited by Gen Agent Trust Hub on Feb 23, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the 'summarize' utility from a third-party Homebrew tap (steipete/tap/summarize). While common for CLI tools, this creates a dependency on an external repository that is not part of the trusted vendors list.\n- [COMMAND_EXECUTION]: The skill executes the 'summarize' binary to process user-provided URLs and file paths. This is the primary function of the skill, and the tool uses various flags and environment variables for its operation.\n- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it processes untrusted data from external sources.\n
  • Ingestion points: The skill ingests content from arbitrary URLs, local files (e.g., PDFs), and YouTube transcripts via the 'summarize' command.\n
  • Boundary markers: No specific boundary markers or instructions to ignore embedded commands are present in the skill's instructions to the agent.\n
  • Capability inventory: The skill executes a binary with network and filesystem access capabilities as part of its normal operation.\n
  • Sanitization: There is no evidence of sanitization or filtering of the content retrieved from external sources before it is returned to the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 23, 2026, 12:56 PM