mission-statement

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill performs legitimate file system operations, reading existing project metadata (e.g., plugin.json, CLAUDE.md) and writing a structured mission.json file to the project root. These actions are consistent with its primary purpose of drafting mission statements.
  • [SAFE]: The skill uses a dedicated MCP tool (mcp__plugin_dh_backlog__backlog_add) to manage development tasks, which is a standard and expected interaction for agentic workflows.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it ingests untrusted data from local project files.
  • Ingestion points: Reads content from plugin.json, CLAUDE.md, SKILL.md, and discuss-CONTEXT.md.
  • Boundary markers: Absent; the instructions do not specify delimiters or warnings to ignore instructions embedded within the analyzed files.
  • Capability inventory: Performs file-write operations (mission.json) and executes a specific MCP tool for backlog management.
  • Sanitization: Absent; the skill does not explicitly filter or validate the content of the analyzed files before using them to generate the draft mission and task description.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 08:41 AM
Security Audit — agent-trust-hub — mission-statement