work-ledger
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill manages a local work ledger using markdown files. It includes a specific security best practice instruction to "Keep secrets, credentials, customer data, and raw transcripts out of it."
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external markdown files in
~/dev/ledger/items/which could contain embedded instructions. - Ingestion points: Reads work item files from
~/dev/ledger/items/<primary-key>.md. - Boundary markers: The skill does not define specific delimiters to separate the ledger content from other agent instructions.
- Capability inventory: The skill has access to the file system (read/write),
git,gh(GitHub CLI), andrg(ripgrep). - Sanitization: There is no mention of sanitizing or escaping the content retrieved from the ledger files before processing.
Audit Metadata