skills/eho/agent-skills/skill-curator/Gen Agent Trust Hub

skill-curator

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection by processing untrusted data from external repositories.
  • Ingestion points: The skill instructions (SKILL.md) direct the agent to read and extract metadata from SKILL.md files found in external GitHub repositories or URLs.
  • Boundary markers: There are no specified boundary markers or delimiters to separate the extracted external content from the agent's internal logic or output formatting.
  • Capability inventory: The skill utilizes file-reading capabilities (via GitHub MCP or Repo Explorer) and file-writing capabilities to update the local README.md catalog.
  • Sanitization: The skill does not include instructions to sanitize, validate, or escape the extracted 'Name' or 'Description' fields before writing them to the local workspace documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 03:29 AM