retro
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data, specifically session logs and repository configuration files, creating a surface for indirect prompt injection.
- Ingestion points: The skill instructions command the agent to read local session logs and repository files such as
package.jsonand CI workflow definitions (found in SKILL.md). - Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from executing instructions that might be embedded within the logs or configuration files being analyzed.
- Capability inventory: The skill requires tools for reading files and searching through system logs to perform its primary function.
- Sanitization: The instructions do not specify any sanitization, filtering, or validation of the external content before it is processed by the agent.
Audit Metadata