sensitive-content-scanner

Warn

Audited by Gen Agent Trust Hub on Jun 30, 2026

Risk Level: MEDIUMDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill instructions direct the agent to access and read highly sensitive file paths, including environment files (.env), configuration directories (~/.claude/), and patterns for private keys and AWS credentials. While this is the intended functionality for a security scanner, it represents a high degree of sensitive data exposure.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests and processes untrusted data from user-provided files without sufficient safety boundaries.
  • Ingestion points: File contents read during the File Discovery and Pattern Scanning phases (described in SKILL.md).
  • Boundary markers: Absent; there are no instructions to use delimiters or to ignore embedded instructions found within the scanned files.
  • Capability inventory: The skill is designed for reading files and generating text reports; no network access or subprocess execution capabilities are specified in the instructions.
  • Sanitization: Absent; scanned content is not sanitized or escaped before being analyzed by the agent.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 30, 2026, 06:29 AM
Security Audit — agent-trust-hub — sensitive-content-scanner