wiki-research

Fail

Audited by Gen Agent Trust Hub on May 8, 2026

Risk Level: HIGHCREDENTIALS_UNSAFEPROMPT_INJECTION
Full Analysis
  • [CREDENTIALS_UNSAFE]: The skill is instructed to read from the .env file as a fallback to retrieve the vault path. Since .env files are high-value targets often containing API keys and other sensitive credentials, this access constitutes a significant security risk.
  • [PROMPT_INJECTION]: The skill executes an autonomous research loop that fetches content from arbitrary external URLs, making it vulnerable to indirect prompt injection.
  • Ingestion points: Data is ingested from the web via WebFetch and defuddle tool outputs (SKILL.md).
  • Boundary markers: The instructions do not define any delimiters or ignore-instructions for the processed external data.
  • Capability inventory: The skill possesses the ability to write to the local filesystem, update manifest files, and modify the index and log files of the Obsidian vault (SKILL.md).
  • Sanitization: No validation or sanitization of the fetched external content is performed before it is synthesized and permanently stored in the vault.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
May 8, 2026, 01:10 PM