writing-beats

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided markdown files ("raw material") to generate content, which creates a surface where malicious instructions embedded in that data could influence the agent's behavior.
  • Ingestion points: The instructions in SKILL.md specify reading a "markdown file of raw material" and an "article file from disk."
  • Boundary markers: The instructions do not define clear delimiters or provide the agent with "ignore embedded instructions" warnings to differentiate between the agent's logic and the potentially untrusted content it processes.
  • Capability inventory: The agent has the capability to perform file read and write operations based on the contents of the processed material.
  • Sanitization: There is no mention of sanitization, validation, or filtering of the external content before it is used to generate or append "beats" to the target file.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 01:52 PM
Security Audit — agent-trust-hub — writing-beats