analyzing-use-cases

Pass

Audited by Gen Agent Trust Hub on Mar 28, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to read and process external data from Jira tickets and research documents, which constitutes an attack surface for indirect prompt injection.\n
  • Ingestion points: Content is ingested from user-provided Jira tickets and research files in Step 1 of the SKILL.md process.\n
  • Boundary markers: The skill lacks explicit instructions for the agent to use delimiters or to disregard potential instructions embedded within the ingested text.\n
  • Capability inventory: The skill can read and write files via TodoWrite, Read, and Grep tools, and its outputs are intended to guide downstream code implementation and testing skills.\n
  • Sanitization: There are no defined sanitization or validation steps for the content extracted from external sources.\n- [COMMAND_EXECUTION]: The skill performs automated file system operations to manage project documentation and configuration.\n
  • Evidence: The process involves reading metadata from $CLAUDE_DOCS_ROOT/projects.yaml and writing use case documents to the $CLAUDE_DOCS_ROOT/use-cases/ directory.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 28, 2026, 10:17 PM
Security Audit — agent-trust-hub — analyzing-use-cases