NYC

project-docs

Fail

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: HIGHPROMPT_INJECTIONNO_CODE
Full Analysis
  • [Indirect Prompt Injection] (HIGH): The skill is susceptible to indirect prompt injection as its core function involves processing untrusted external content.\n
  • Ingestion points: Ingests code changes and documentation files for processing via the docs-excellence-architect subagent (specified in SKILL.md).\n
  • Boundary markers: Absent. The example prompt does not include delimiters to separate instructions from untrusted input data.\n
  • Capability inventory: The subagent is instructed to update or propose updates to project files (README.md, guides, etc.), which represents a file-modification capability.\n
  • Sanitization: No evidence of sanitization or validation of the input content is provided.\n- [No Code] (LOW): The skill consists entirely of markdown instructions and does not include any executable scripts, binaries, or package dependencies.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 16, 2026, 05:51 AM