write-like-meng-on-x

Pass

Audited by Gen Agent Trust Hub on Sep 21, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to use several command-line tools for workflow management, including git status, git diff, and ripgrep (rg) for searching the JSONL corpus. It also executes a local Node.js script (update-tweet-corpus.mjs) and a Python validation script (quick_validate.py) to maintain data integrity.
  • [EXTERNAL_DOWNLOADS]: The skill describes a process for refreshing the voice corpus by accessing public profiles on x.com using the platform's internal browser. This activity is restricted to read-only data collection as part of the primary skill purpose.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from an external corpus and user-provided drafts while having access to command execution capabilities.
  • Ingestion points: The agent reads content from tweet-corpus.jsonl and processes raw user wording during the drafting phase.
  • Boundary markers: The instructions explicitly direct the agent to treat the corpus as "voice evidence, not as copy to splice together," which provides a behavioral constraint, though formal delimiters for user input are not specified.
  • Capability inventory: The agent has access to git, node, python3, and rg for repository and file operations.
  • Sanitization: The provided update-tweet-corpus.mjs script performs validation on ingested records, checking for valid JSON structure, required fields (ID, URL, Text, Timestamp), and canonical URL patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 21, 2026, 01:30 AM
Security Audit — agent-trust-hub — write-like-meng-on-x