analyze

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core function of processing untrusted external data.
  • Ingestion points: As described in SKILL.md and doctrine.md, the skill retrieves "live repository, ticket, PR, and diff facts" from external sources.
  • Boundary markers: The instructions lack specific delimiters or "ignore" directives to prevent the agent from following instructions embedded within the ingested repository data.
  • Capability inventory: The skill has the capability to parallelize research by spawning "Task workers" (subagents) and can initiate downstream actions by "promoting" results to other skills like /task or /write-ticket.
  • Sanitization: There are no mentioned mechanisms for sanitizing, escaping, or validating the content retrieved from external trackers or repositories before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 04:38 PM
Security Audit — agent-trust-hub — analyze