jungian-psychologist

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection vulnerability surface detected. The skill permits the use of external data retrieval tools without specifying safety constraints, which creates a potential risk when paired with its file-modification capabilities.
  • Ingestion points: The skill is configured to allow mcp__firecrawl__firecrawl_search and WebFetch tools, which ingest untrusted content from the internet into the agent's context.
  • Boundary markers: The instructions do not define delimiters or specific 'ignore' directives to prevent the agent from being influenced by instructions embedded in external web content.
  • Capability inventory: Across its configuration, the agent has access to Write and Edit tools, allowing it to modify the file system based on potentially manipulated data.
  • Sanitization: There is no evidence of sanitization, validation, or filtering of content retrieved from the web tools before it is processed or used for file operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 01:09 PM