pharma-compliance
Pass
Audited by Gen Agent Trust Hub on Mar 23, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection. It processes untrusted data from project files (SOPs, CAPA records, logs) and interpolates user-provided
$ARGUMENTSdirectly into the analysis prompt without explicit boundary markers or sanitization. Maliciously crafted content within the audited files could potentially influence the agent's behavior during the assessment. - Ingestion points: The skill reads various quality management system (QMS) components and regulatory records from the project directory (SKILL.md).
- Boundary markers: None identified; content is processed directly as part of the discovery and assessment phases.
- Capability inventory: The skill is designed for the
CLAUDE_CODEplatform, which typically provides file system access. The skill specifically instructs writing telemetry data to~/.claude/projects/. - Sanitization: No sanitization or validation of the processed data is specified.
Audit Metadata