tldr-generator
Pass
Audited by Gen Agent Trust Hub on Apr 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill facilitates the execution of internal Node.js and Python scripts to analyze articles and validate generated summaries. This is an expected part of the skill's workflow.
- [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it processes untrusted markdown content. 1. Ingestion points: Markdown files identified in the workspace are read into the agent's context via scripts. 2. Boundary markers: There are no explicit delimiters or instructions provided to isolate processed content from the agent's core logic. 3. Capability inventory: The agent can execute local scripts and perform file system operations. 4. Sanitization: The skill includes preventative instructions in SKILL.md directing the agent to avoid reproducing sensitive data like tokens or emails in the final output.
Audit Metadata