praxis-direction
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from local project files that may be under the control of third parties in a shared repository environment.
- Ingestion points: The agent is instructed to read configuration and context from
AGENTS.md,PROJECT.md, andpraxis-profile.mdlocated within the user's workspace. - Boundary markers: The instructions do not define explicit delimiters or boundary markers to prevent the agent from following instructions potentially embedded within these project files.
- Capability inventory: The skill possesses the capability to write to and modify project files (
praxis-profile.md,AGENTS.md,PROJECT.md), creating a surface where malicious context could influence file modifications. - Sanitization: There is no specific validation or sanitization step mentioned for the data retrieved from workspace files before it is processed or written back to the profile.
Audit Metadata