obsidian-work-log-release-recorder
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user descriptions of coding, deployment, and configuration tasks to generate durable documentation, creating a path for untrusted data to enter the agent context.
- Ingestion points: External data enters via user prompts summarizing completed work, which may include third-party scripts, logs, or configuration snippets.
- Boundary markers: The instructions do not mandate the use of delimiters or 'ignore' instructions when writing user-provided task summaries into the vault notes.
- Capability inventory: The agent has permissions to read and write markdown files within the specific local path
/Users/huangrx6/Documents/obsidian. - Sanitization: The skill explicitly forbids recording secrets like passwords or tokens, which is a positive safety control, but it lacks mechanisms to sanitize the content for embedded prompt injection instructions.
Audit Metadata