stakeholder-update
Pass
Audited by Gen Agent Trust Hub on Jul 1, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection by ingesting untrusted data from external sources to generate its output.
- Ingestion points: According to the workflow in
SKILL.md, the agent accepts project facts from PR descriptions, technical documents, and vault note paths. - Boundary markers: The instructions do not specify any delimiters (e.g., XML tags or triple quotes) or provide guidance to the agent to disregard instructions embedded within the provided source materials.
- Capability inventory: The skill includes a file-write capability, as noted in the behavior section of
SKILL.mdwhich instructs the agent to save output to specific paths within the 'vault/' directory. - Sanitization: There are no documented steps for escaping, validating, or filtering the external content before it is processed by the LLM.
Audit Metadata