pp-techmeme

Pass

Audited by Gen Agent Trust Hub on May 12, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the techmeme-pp-cli binary using go install from a GitHub repository associated with the author (github.com/mvanhorn/printing-press-library). It also supports installation via a vendor-associated npm package (@mvanhorn/printing-press).
  • [COMMAND_EXECUTION]: The skill executes the techmeme-pp-cli tool to interact with news data. The tool includes functionality for local data storage and features a --deliver flag that allows routing command output to local files or remote webhooks.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes news headlines and search results from Techmeme, an external source.
  • Ingestion points: Untrusted news data enters the agent context via the river, search, and since commands as described in SKILL.md.
  • Boundary markers: No specific delimiters or safety instructions are defined to separate the ingested news content from the agent's core instructions.
  • Capability inventory: The techmeme-pp-cli tool possesses capabilities for file system modification and network communication (webhooks).
  • Sanitization: The skill documentation does not mention any sanitization or validation of the ingested headline data.
Audit Metadata
Risk Level
SAFE
Analyzed
May 12, 2026, 02:40 AM