xxxxxx-for-astra
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and modify instruction files (such as SKILL.md, AGENTS.md, and CLAUDE.md) which may contain untrusted content from third-party sources.
- Ingestion points: The workflow involves inventorying and reviewing active instruction sources, skill manifests, and recursively exposed manifests across the agent's environment.
- Boundary markers: There are no explicit instructions for the agent to use XML-like tags or specific delimiters to isolate the content being audited from its own operational logic, increasing the risk of the agent following instructions found within the audited files.
- Capability inventory: The skill instructs the agent to "Apply only requested changes through the canonical source of truth," which requires file-write capabilities in the execution environment.
- Sanitization: The audit process does not include specific validation or sanitization steps to prevent instructions inside the target files from being interpreted as commands by the auditing agent.
Audit Metadata