agentskills-project-onboarding
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to inspect repository files (source code, documentation, CI/CD configs) to determine appropriate configurations. This creates an attack surface where malicious instructions embedded in a repository could influence the agent's behavior or recommendations.
- Ingestion points:
SKILL.md(Core Workflow step 1) instructs the agent to inspect various repo files. - Boundary markers: The instructions lack specific requirements for boundary delimiters or explicit 'ignore instructions' markers when processing external data.
- Capability inventory: The skill itself is instructional and lacks defined tool capabilities, but it instructs an agent that likely possesses file-system and command-execution tools.
- Sanitization: The workflow does not define methods for sanitizing or filtering instructions encountered during repository inspection.
Audit Metadata