cs-note
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill manages project-specific context within a local file (
.codestable/attention.md). No malicious patterns, external downloads, or exfiltration vectors were detected. - [PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by maintaining a "mandatory read context" file that influences the agent's future behavior. This is the primary intended function of the skill.
- Ingestion points:
.codestable/attention.md(read as mandatory context) - Boundary markers: Absent; instructions state the agent must check this file before any action.
- Capability inventory: Reading and writing to the local filesystem (specifically
.codestable/). - Sanitization: Absent; content is appended based on user snippets or observed project settings.
Audit Metadata