auditar-drift
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection by ingesting and processing untrusted project files and source code. Malicious instructions embedded in the audited documents or code comments could attempt to influence the agent's analysis or the content of the generated report.
- Ingestion points: Ingests content from
PRD.md,adrs/*.md,TECH-DESIGN.md, and the full project source codebase. - Boundary markers: The instructions do not specify the use of delimiters or boundary markers when interpolating untrusted data into the context, although the workflow requires specific textual citations for findings.
- Capability inventory: The skill is authorized to read the codebase and write a local
DRIFT.mdfile; it does not utilize network operations, dynamic code execution, or elevated system privileges. - Sanitization: No explicit sanitization or filtering mechanisms are defined for the data extracted from the source files before it is processed or written to the output report.
Audit Metadata