testing
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches the Photon indexer source code and binaries from the Light Protocol GitHub repository and Helius infrastructure.
- Evidence:
cargo install --git https://github.com/lightprotocol/photon.gitinreferences/local.mdand prover binary locations in~/.config/light/bin/. - [COMMAND_EXECUTION]: The skill utilizes standard development tools and vendor-specific CLIs to manage test environments and execute program tests.
- Evidence: Usage of
light test-validator,cargo test-sbf, andpnpm test-validatoracrossSKILL.mdandreferences/local.md. - [INDIRECT_PROMPT_INJECTION]: The skill utilizes the
HELIUS_API_KEYenvironment variable to authenticate RPC requests to external providers. - Ingestion points:
HELIUS_API_KEYenvironment variable (declared inSKILL.mdfrontmatter). - Boundary markers: The skill instructs the agent to use
AskUserQuestionto resolve ambiguities before execution. - Capability inventory: The agent has access to shell commands (
light,cargo,node) and file system operations. - Sanitization: Not explicitly implemented, but the API key is used within template strings for RPC URLs as standard practice.
Audit Metadata