external-resource-context
Pass
Audited by Gen Agent Trust Hub on Jul 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill facilitates the creation of a centralized project context file (
docs/project-context/external-resources.md) by guiding the agent to ask the user structured questions about their environment. - [DATA_EXFILTRATION]: While the skill gathering information about secret store locations and environment configurations could be sensitive, it specifically records this data into a local documentation file as part of its documented purpose. There is no evidence of these details being transmitted to external or unauthorized systems.
- [COMMAND_EXECUTION]: The skill defines a protocol for recording reference commands (such as database migration or visual verification commands) within the project documentation. These commands are provided by the user and intended for future manual or agent-assisted reference.
- [PROMPT_INJECTION]: The skill establishes a 'Lookup Protocol' for agents to consume the documentation it generates. It relies on user-verified inputs via the 'Hearing Protocol' to populate its templates, minimizing the risk of accidental or malicious instructions being processed.
- Ingestion points: User answers provided during the Hearing Protocol defined in SKILL.md.
- Boundary markers: Data is structured into specific markdown tables as defined in references/template.md.
- Capability inventory: File system write operations for documentation management (SKILL.md).
- Sanitization: None, the skill relies on the human user to provide accurate and safe configuration details.
Audit Metadata