sprint-plan

Pass

Audited by Gen Agent Trust Hub on Mar 21, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is subject to indirect prompt injection because it ingests and processes untrusted data from GitHub issues to perform classification, effort estimation, and sprint assignment.
  • Ingestion points: Untrusted data enters the agent's context via the gh issue list and gh api commands, which fetch issue titles, labels, and milestones from the IBM/mcp-context-forge repository (SKILL.md).
  • Boundary markers: There are no explicit boundary markers or delimiters defined in the instructions to separate the external data from the agent's internal logic or instructions.
  • Capability inventory: The agent utilizes the gh CLI tool and its internal code execution capabilities (Python) to manipulate the data and generate artifacts like CSV files.
  • Sanitization: The skill lacks instructions for sanitizing or validating the content of the issues before the agent processes them.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 21, 2026, 06:35 AM
Security Audit — agent-trust-hub — sprint-plan