Project Management

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests data from external project management tools like Jira and GitHub Issues.
  • Ingestion points: Backlog items and task updates are imported from external APIs into the agent context in the workflow.
  • Boundary markers: There are no instructions to use delimiters or ignore instructions within the imported project data.
  • Capability inventory: The agent can perform write actions on project trackers and post to Slack or Teams channels.
  • Sanitization: The skill does not specify procedures for sanitizing or validating the content retrieved from external trackers.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 12:34 PM