sgc-electron-delta-updater
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external public release pages and update feeds (appcast files) to verify deployment results, creating an attack surface where malicious data could influence agent behavior.
- Ingestion points: Public GitHub/release pages and remote appcast/delta metadata files (SKILL.md, references/release-verification.md).
- Boundary markers: The instructions do not specify using delimiters or clear separation between system instructions and untrusted external content.
- Capability inventory: The skill workflow includes running project-specific build, packaging, signing, and testing commands (SKILL.md).
- Sanitization: There is no requirement in the instructions to sanitize or escape data fetched from external feeds before it is used in the context.
- [COMMAND_EXECUTION]: The skill is designed to invoke the host project's build, signing, and testing tools to validate the update pipeline (SKILL.md, README.md). This behavior is consistent with the skill's purpose as a developer tool but involves executing arbitrary shell commands provided by the target project.
Audit Metadata