orient
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and process data from external and potentially untrusted sources (e.g.,
README.md,docs/adr/,CONTEXT.md, test files, and general codebase symbols). This creates an attack surface where malicious instructions hidden in the project documentation could be interpreted by the agent during its "orientation" phase. - Ingestion points: The skill explicitly instructs the agent to read various files across the repository, including
CONTEXT.md,docs/adr/,.claude/rules/,DEVELOPMENT.md, and any local knowledge base viaknowledge_searchorkb_read. - Boundary markers: The instructions do not specify the use of delimiters or provide warnings for the agent to ignore instructions or command-like text found within the terrain files.
- Capability inventory: While this specific skill is described as "read-only," the bearing it produces is intended to be consumed by subsequent skills or tools which may have the capability to execute commands, write files, or perform network operations.
- Sanitization: No sanitization or validation of the content of the project files is performed before the information is extracted into the "bearing" summary.
Audit Metadata