setup-chalk

Pass

Audited by Gen Agent Trust Hub on Jun 27, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill displays an attack surface for indirect prompt injection by design, as its primary function is to read and interpret content from untrusted repository files to generate documentation.\n
  • Ingestion points: Phase 1 and Phase 2 of the workflow read content from README.md, dependency manifests (package.json, pyproject.toml, etc.), configuration files, and source code files.\n
  • Boundary markers: The skill does not define specific delimiters or instructional boundaries to isolate the ingested repository content from the agent's processing logic.\n
  • Capability inventory: The skill is configured with Read, Write, Glob, Grep, and Bash capabilities.\n
  • Sanitization: No explicit sanitization or content validation is mentioned for the data extracted from the repository files.\n- [COMMAND_EXECUTION]: The skill uses Bash and Grep to explore the repository structure. While these tools are used for project analysis, the inclusion of user-provided arguments in shell-based discovery phases creates a potential surface for command injection if path inputs are not handled with appropriate caution.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 27, 2026, 03:40 AM
Security Audit — agent-trust-hub — setup-chalk