tsl
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process various external project files, creating a vector for indirect prompt injection if those files are attacker-controlled.\n
- Ingestion points: The agent reads
package.json, renderer configurations, material source files, GLSL shader code, and test files (SKILL.md,migration.md).\n - Boundary markers: No explicit instructions or delimiters are provided to the agent to treat external content as untrusted data or to ignore embedded instructions.\n
- Capability inventory: The skill enables file reading/writing, shell command execution via
pnpm, and shader execution in a browser context (typescript.md,verification.md).\n - Sanitization: No evidence of sanitization or validation of external content was found.\n- [COMMAND_EXECUTION]: The skill provides explicit instructions to execute shell commands for type checking and verification.\n
- Evidence:
typescript.mdcontains instructions to runpnpm --filter @pmndrs/glyph typecheck:slug-tslandpnpm --filter @pmndrs/glyph typecheck. While these are targeted at project-specific build tools, they establish a pattern of the agent executing shell commands based on skill instructions.
Audit Metadata