project-goal
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the local repository, creating a potential surface for indirect prompt injection.
- Ingestion points: The workflow in
SKILL.mdrequires the agent to read various project files includingREADME.md, package manifests, configuration files, and source code to form a working theory. - Boundary markers: The skill does not define specific delimiters or instructions to ignore commands that might be embedded within the project files it reads.
- Capability inventory: The skill is permitted to write and update the
GOAL.mdfile in the project root as described inSKILL.md. - Sanitization: The instructions do not specify any sanitization or validation logic for the data gathered from the repository before it is used to generate the final document.
Audit Metadata