lab-automation
Pass
Audited by Gen Agent Trust Hub on Mar 23, 2026
Risk Level: SAFEPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [PROMPT_INJECTION]: The skill uses the
$ARGUMENTSvariable to allow users to specify a focus area for the audit. This creates a surface where untrusted data could potentially override agent instructions. - Ingestion points: SKILL.md (SCOPE: $ARGUMENTS)
- Boundary markers: Absent. The input is interpolated directly without delimiters or safety warnings.
- Capability inventory: The skill has the ability to write files to the local directory (docs/lab-automation-analysis.md) and the user's home directory (~/.claude/projects/).
- Sanitization: No validation or escaping of input data is performed before processing.
- [DATA_EXFILTRATION]: The skill implements a 'Self-Evolution Telemetry' feature that writes execution metadata to
~/.claude/projects/skill-telemetry.md. This is a local data logging behavior and does not involve transmitting data to a remote server.
Audit Metadata