writing-fragments

Pass

Audited by Gen Agent Trust Hub on Sep 22, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill reads content from a user-specified markdown file on the local file system. This ingested content could contain malicious instructions that attempt to influence the agent's behavior.
  • Ingestion points: The skill reads a markdown file at a path specified by the user during the session (reference: SKILL.md).
  • Boundary markers: Absent. The instructions do not define specific delimiters or warnings to separate the file's content from the agent's operational instructions.
  • Capability inventory: The skill has the capability to read from and append to the local file system.
  • Sanitization: Absent. There are no instructions provided to sanitize, filter, or validate the content retrieved from the file before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 22, 2026, 09:46 AM
Security Audit — agent-trust-hub — writing-fragments