jmb-retro
Pass
Audited by Gen Agent Trust Hub on Nov 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes historical session logs as its primary input, which creates a potential attack surface for indirect prompt injection.
- Ingestion points: Step 2 in SKILL.md instructs the agent to read and search through session logs on the local machine.
- Boundary markers: The instructions do not provide delimiters or explicit directives to ignore embedded instructions within the logs.
- Capability inventory: While the skill itself is instructional, it directs the agent to propose modifications to high-impact steering and configuration files like AGENTS.md, CLAUDE.md, and CODING_STANDARDS.md.
- Sanitization: There is no mechanism described for the validation or sanitization of content extracted from the logs before the agent analyzes and acts upon it.
Audit Metadata