dev-swarm-refine-mcp-skill-descriptions

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect prompt injection surface.
  • Ingestion points: Content is read from the 'description' field of 'dev-swarm/mcp-skills/**/SKILL.md' files.
  • Boundary markers: None. The skill does not use delimiters to isolate the description text from the agent's instructions.
  • Capability inventory: The agent has capabilities to read and write files within the 'dev-swarm/' directory.
  • Sanitization: No filtering or validation of the ingested description content is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 08:28 PM