obsidian-source-ingestion
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external content (web pages, papers, and transcripts) and uses it to update internal project files (_system/registry.md, 02-Index.md, and Daily/ notes). This creates a surface where malicious instructions embedded in a source document could influence the agent's behavior during the ingestion process.
- Ingestion points: Processes external materials to create notes in Sources/ directories as described in SKILL.md.
- Boundary markers: Absent; no instructions are provided to the agent to disregard embedded directives in source materials.
- Capability inventory: File system write access to update registries, indexes, and logs across the Obsidian vault.
- Sanitization: Absent; the skill does not specify filtering or validation of the ingested text to prevent command or prompt injection.
Audit Metadata