asb-interview-learning
Pass
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions do not contain any evidence of malicious code, data exfiltration, or unauthorized network activity. All operations involve reading and writing local project files (
HYPOTHESES.md,QUESTIONS.md) within the agent's environment. - [PROMPT_INJECTION]: The skill is designed to ingest and process potentially untrusted data from interview debrief files, creating a surface for indirect prompt injection.
- Ingestion points: The agent reads all files within a user-specified
interviews/directory. - Boundary markers: While no specific data delimiters are mentioned for the ingestion phase, the skill enforces a strict human-in-the-loop requirement for every change. Users must manually review and approve each proposed update, preventing automated execution of injected instructions.
- Capability inventory: The skill uses file read and write tools to manage project documentation.
- Sanitization: There is no mention of automated sanitization or filtering of the ingested interview content.
Audit Metadata