wiki-research-personal

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external web sources and a shared queue file, which could be used to influence the agent's behavior. However, the potential impact is mitigated by the skill's restricted file-writing permissions within the vault workspace.\n
  • Ingestion points: Research queue items read from RESEARCH_QUEUE.md and external information retrieved through web_search and intelli_extract.\n
  • Boundary markers: There are no explicit instructions or delimiters used to separate the untrusted data from the agent's core processing logic or to warn the agent about potentially malicious content.\n
  • Capability inventory: The skill is capable of reading and writing markdown files in the /app/data/vault/ directory and performing web searches using the Brave engine.\n
  • Sanitization: The skill does not implement any mechanisms to sanitize, escape, or validate the content retrieved from external sources before it is processed or stored.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 11:52 AM
Security Audit — agent-trust-hub — wiki-research-personal