docs-update

Pass

Audited by Gen Agent Trust Hub on Sep 23, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process source code, configuration, and documentation files which are external and potentially untrusted data sources.
  • Ingestion points: Processes repository code, config, tests, and internal/user-facing documentation (SKILL.md).
  • Boundary markers: No explicit delimiters or safety instructions are provided to distinguish between documentation content and potential instructions.
  • Capability inventory: The skill allows editing of authoritative sources and execution of repository scripts and code examples (SKILL.md).
  • Sanitization: No sanitization or validation of the file content is performed before processing.
  • [COMMAND_EXECUTION]: The agent is instructed to run repository-specific tools, scripts, and examples to verify documentation accuracy. This capability could be exploited to execute malicious code if the repository itself is compromised or contains adversarial content.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 23, 2026, 04:19 AM
Security Audit — agent-trust-hub — docs-update