writing-fragments

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's logic is restricted to local file operations and user interaction for writing purposes. No malicious patterns, obfuscation, or unauthorized access attempts were identified.\n- [INDIRECT_PROMPT_INJECTION]: The skill reads project context from ../../WORK-ROUTING.md and user-generated fragments, which serves as a potential ingestion point for external content. However, the risk is considered safe due to the restricted capabilities provided to the agent. \n
  • Ingestion points: The agent reads the ../../WORK-ROUTING.md file and the user-specified fragment markdown file. \n
  • Boundary markers: The fragment file uses horizontal rules (---) to separate content. \n
  • Capability inventory: The agent is limited to reading and appending to text files within the local environment. \n
  • Sanitization: No sanitization or escaping of the content read from these files is implemented.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 06:42 AM
Security Audit — agent-trust-hub — writing-fragments