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.mdandlog.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