skills/salavender/antigravity-compound-engineering-plugin/standard-security-auth/Gen Agent Trust Hub
standard-security-auth
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill contains an instrumentation step that instructs the agent to execute a local shell script at
./scripts/log-skill.shto log skill usage. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to trigger when the agent interacts with security-critical files such as
middleware.ts,AuthContext.tsx, andapiClient.ts. - Ingestion points: The skill monitors
middleware.ts,**/auth/**,app/contexts/AuthContext.tsx, andlib/apiClient.ts. - Boundary markers: None are specified to distinguish between the skill's instructions and potentially malicious content within the monitored files.
- Capability inventory: The skill has the capability to execute shell commands via the logging script.
- Sanitization: No explicit sanitization or validation of the content within the monitored files is defined, creating a potential surface for instructions embedded in those files to influence the agent's behavior.
Audit Metadata