wiki-stage-commit

Pass

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes content from the _staging/ directory, which represents a potential attack surface for indirect prompt injection.\n
  • Ingestion points: Markdown and patch files are read from the $OBSIDIAN_VAULT_PATH/_staging/ directory (SKILL.md Step 1).\n
  • Boundary markers: There are no explicit instructions or delimiters used to separate untrusted content from the agent's instructions during the preview or application phases.\n
  • Capability inventory: The skill is capable of moving files across directories, modifying file content (merging patches), and updating tracking files like hot.md and log.md (SKILL.md Step 3 and 4).\n
  • Sanitization: No sanitization or content validation is performed on the files before they are previewed for the user or merged into the live wiki.
Audit Metadata
Risk Level
SAFE
Analyzed
May 18, 2026, 05:09 PM
Security Audit — agent-trust-hub — wiki-stage-commit