obsidian-source-ingestion
Pass
Audited by Gen Agent Trust Hub on Apr 25, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill instructions facilitate the ingestion of potentially untrusted external data (such as web pages, papers, and data) into a local knowledge base, which presents an indirect prompt injection surface. Ingestion points: External materials described in SKILL.md and references/SOURCE-TYPES.md are brought into the agent's context. Boundary markers: The provided instructions do not define delimiters or special handling to isolate external content from the agent's core instructions. Capability inventory: The skill directs the agent to perform file write operations to various locations including Sources/, _system/registry.md, 02-Index.md, and Daily/ notes. Sanitization: No sanitization, validation, or escaping mechanisms for the ingested content are specified.
- [NO_CODE]: The skill is composed entirely of markdown instructions and reference templates; it does not contain any executable scripts, binary files, or installation dependencies.
Audit Metadata