writing-beats

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied markdown files as "raw material," which serves as an ingestion point for untrusted data.
  • Ingestion points: The agent is instructed to read a markdown file provided by the user and "mine the pile" to populate article beats.
  • Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore potentially malicious embedded commands within the raw material.
  • Capability inventory: The skill utilizes file read and write operations on paths provided by the user.
  • Sanitization: There is no explicit requirement for the agent to sanitize or filter content extracted from the input files.
  • [SAFE]: The skill uses the term "exploit" in a literary context to describe a phase of the writing workflow rather than a security vulnerability. No evidence of obfuscation, unauthorized network activity, or credential theft was found.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 01:03 AM
Security Audit — agent-trust-hub — writing-beats