festival-intake

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill directs the agent to interact with the filesystem and version control system using the 'fest' utility.
  • Evidence: Instructions include the execution of fest create workflow, fest create festival, fest next, fest validate, fest commit, and fest task completed across various stages of the project lifecycle.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon untrusted data provided by users, which creates a surface for indirect instructions to influence the agent.
  • Ingestion points: The skill explicitly triggers when a user 'hands over a spec, a ticket, or a document' as noted in the frontmatter description.
  • Boundary markers: There are no instructions provided to the agent to treat the content of these external documents as data rather than instructions, nor are there delimiters defined to isolate this content.
  • Capability inventory: The agent is granted the ability to create project structures, write task files, and perform commits (fest commit) based on the content of the ingested data.
  • Sanitization: The instructions lack requirements for sanitizing or validating the content of the external specifications before they are incorporated into the 'festival' plan.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 06:04 AM
Security Audit — agent-trust-hub — festival-intake