project-knowledge

Pass

Audited by Gen Agent Trust Hub on Nov 12, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting and acting upon untrusted data from repository documentation files. \n- Ingestion points: The skill reads GLOSSARY.md, DESIGN.md, and other documentation in docs/decisions/ to identify settled rules and terms (SKILL.md). It also specifically parses the ## Issue tracker section of AGENTS.md or CLAUDE.md to determine how to create issues. \n- Boundary markers: The instructions do not define or require the use of boundary markers or specific delimiters to separate user/agent instructions from the content of the files being read. \n- Capability inventory: The skill possesses capabilities to write to the local file system (creating/updating markdown files) and to interact with external issue tracking tools based on instructions found within the project's own files. \n- Sanitization: There is no mention of sanitizing, escaping, or validating the content read from these external files before it is processed or used to influence the agent's logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 12, 2026, 08:26 AM