factory-lookback
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill aggregates data from several untrusted sources, creating a surface for indirect prompt injection.
- Ingestion points: According to SKILL.md, the agent reads .agent-factory/config.yaml and clusters data from feedback, analytics, telemetry, runtime errors, CI failures, and replies to information requests.
- Boundary markers: There are no instructions to ignore embedded commands or use specific delimiters to isolate the ingested data.
- Capability inventory: The skill enables the agent to implement systemic fixes, recommend changes, and interact with PR or deployment processes via the workflows.lookback.implement workflow.
- Sanitization: No validation or sanitization of external content is mentioned in the audit or implementation steps.
Audit Metadata