regex-mastery
Warn
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill contains instructions and links to install companion skills from the
AbsolutelySkilledGitHub organization using thenpx skills addcommand. This organization is not a recognized trusted vendor or well-known service, which introduces risks associated with installing and executing unverifiable third-party code. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-supplied text for pattern matching and validation, creating a surface for indirect prompt injection attacks.
- Ingestion points: User-provided text strings for regex matching, extraction, and validation tasks defined in
SKILL.md. - Boundary markers: Absent; the skill does not specify delimiters or instructions to prevent the agent from obeying embedded directives in the input text.
- Capability inventory: None detected; the skill provides examples and documentation rather than functional scripts or tool invocations.
- Sanitization: Absent; no logic is provided to sanitize or escape external content before processing.
Audit Metadata