skills/dydoc/skills/writing-beats/Gen Agent Trust Hub

writing-beats

Pass

Audited by Gen Agent Trust Hub on Sep 12, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes raw markdown material provided by the user, which serves as an ingestion point for potentially untrusted data that could influence the agent's writing behavior.
  • Ingestion points: Markdown file of raw material (SKILL.md).
  • Boundary markers: No explicit delimiters or boundary markers are defined to isolate untrusted data from the agent's instructions.
  • Capability inventory: The skill includes instructions to read from and write to the local file system (SKILL.md).
  • Sanitization: No sanitization or content validation procedures are specified for the raw material.
  • [COMMAND_EXECUTION]: The skill directs the agent to interact with the local file system by reading and writing files. While these operations are directed by user-provided paths, they involve the execution of system-level commands by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 12, 2026, 06:28 AM
Security Audit — agent-trust-hub — writing-beats