retro-wx
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes historical session data which constitutes an attack surface for indirect prompt injection if the ingested logs contain adversarial instructions.
- Ingestion points: Retrieves session records from a local agent-sessions service at
http://127.0.0.1:8390or uses current session context (SKILL.md). - Boundary markers: The instructions lack explicit delimiters or warnings to the agent to treat the session data as potentially untrusted content or to ignore embedded instructions.
- Capability inventory: The agent is authorized to propose (and upon user approval, implement) modifications to critical project configurations, including
package.json, pre-commit hooks, CI workflows, and the user's personal skills repository (SKILL.md). - Sanitization: There is no mechanism described for sanitizing or validating the content of the sessions before analysis.
Audit Metadata