repo-standards-enforcement
Pass
Audited by Gen Agent Trust Hub on Mar 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to resolve and execute commands from repository-native sources such as
package.jsonmanifests and workspace tooling. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the ingestion of repository configuration data.
- Ingestion points: Repository artifacts including
package.json,tsconfig.json,Pulumi.yaml, and lockfiles mentioned in SKILL.md. - Boundary markers: Absent; the skill does not define specific delimiters or instructions to ignore malicious content within analyzed repository files.
- Capability inventory: Extensive capability to execute shell commands via
bunx,tsc,bun test, and various package manager scripts. - Sanitization: Absent; the instructions lack specific validation or sanitization steps for commands extracted from the repository's environment.
Audit Metadata