agent-documentation-scribe

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is designed to analyze and summarize external, potentially untrusted data such as source code and existing documentation files.
  • Ingestion points: Reads various local project files (ROADMAP, API_REFERENCE, source code) to generate documentation.
  • Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are defined to separate ingested data from the agent's system instructions.
  • Capability inventory: The agent has access to significant capabilities including Bash, WebFetch, Write, and mcp__brave__brave_web_search.
  • Sanitization: There is no evidence of sanitization or filtering of the content read from files before it is processed by the agent.
  • [COMMAND_EXECUTION]: The imported agent specification includes the Bash tool. While this tool is intended for documenting and verifying code examples, its presence as a capability alongside data ingestion surfaces increases the potential impact of a successful injection attack.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 01:13 AM