doc-updater

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted external documentation which may contain malicious instructions.
  • Ingestion points: Documentation, READMEs, release notes, and operating docs (SKILL.md).
  • Boundary markers: No explicit delimiters are provided to separate untrusted content from system instructions.
  • Capability inventory: Terminal command execution via the ExecutionProxy interface and persistent artifact creation via MemoryStore.
  • Sanitization: The skill includes an explicit protocol to treat external data as hostile and redact secrets or PII before sharing context.
  • [COMMAND_EXECUTION]: The skill utilizes a specific command interface for terminal actions.
  • Evidence: Instructs the use of an execution prefix (rtk) for terminal commands, such as rtk npm test, to monitor and control execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 07:36 AM
Security Audit — agent-trust-hub — doc-updater