to-spec

Pass

Audited by Gen Agent Trust Hub on Sep 22, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted conversation history to generate content that is then published to a project issue tracker.
  • Ingestion points: Processed data includes the "current conversation context" and "codebase understanding" (SKILL.md).
  • Boundary markers: The skill provides a structured markdown <spec-template> to guide the synthesis of information.
  • Capability inventory: The skill utilizes repository exploration tools and issue tracker publishing capabilities, including the ability to apply triage labels such as ready-for-agent that may trigger downstream automation.
  • Sanitization: There are no explicit instructions to sanitize or validate the conversation history for malicious instructions before publishing to the external tracker.
  • [COMMAND_EXECUTION]: The skill directs the agent to "Explore the repo to understand the current state of the codebase," which involves the use of file system traversal and search tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 22, 2026, 11:39 PM
Security Audit — agent-trust-hub — to-spec