woostack-plan
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is instructed to ingest and follow instructions from untrusted external files.
- Ingestion points: The skill reads all files within
.woostack/wisdom/*.mdand the user-specified spec file in.woostack/specs/(as defined inSKILL.md). - Boundary markers: No boundary markers, XML tags, or delimiters are specified to isolate the content of these external files from the agent's system instructions.
- Capability inventory: The skill performs file system write operations by creating or amending markdown files in the
.woostack/plans/directory. - Sanitization: No validation, escaping, or filtering of the content from the wisdom or spec files is mentioned.
Audit Metadata