implement-spec

Pass

Audited by Gen Agent Trust Hub on Oct 22, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon specifications and tickets from external sources such as issue trackers. * Ingestion points: Subagents are instructed to "Read the spec and tickets" (SKILL.md). * Capability inventory: The agents can perform git operations (branching, merging), write files to the host system ("save its markdown notes in a directory outside the repo"), and execute tools (tdd, code-review). * Boundary markers: No delimiters or instructions are provided to the agent to treat external content as untrusted or to ignore embedded commands. * Sanitization: No sanitization or validation logic is defined for the content retrieved from external sources.
  • [COMMAND_EXECUTION]: The skill facilitates the execution of git commands and development tools (tdd, code-review). While intended for development, the lack of input validation on the external specifications that drive these actions could be exploited to perform unintended operations through the subagents.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 22, 2026, 03:51 PM