gsd-inbox
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data in the form of GitHub issues and pull request content.
- Ingestion points: The skill fetches open issues and PRs from GitHub repositories (SKILL.md).
- Boundary markers: There are no explicit instructions or delimiters defined to separate the fetched content from the agent's instructions.
- Capability inventory: The skill has access to powerful tools including
Bash,Write,Read,Grep, andGlob(SKILL.md). - Sanitization: No sanitization or validation of the fetched GitHub content is mentioned before it is reviewed by the agent.
- Risk: An attacker could craft a GitHub issue or PR containing malicious instructions that, when read by the agent, might cause it to execute unauthorized commands or modify local files using its available tools.
Audit Metadata