meta-issue-creation
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using the GitHub CLI (
gh) for searching repositories (gh search issues) and creating issues (gh issue create). These operations target repositories within thecipherstashorganization, which is consistent with the skill's stated purpose. - [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow where the agent ingests external data from GitHub issue search results. This presents a potential surface for indirect prompt injection if an issue title or description contains malicious instructions meant to influence the agent's subsequent actions.
- Ingestion points: Data retrieved from
gh search issues --repo cipherstash/stack(SKILL.md). - Boundary markers: Absent; there are no explicit instructions for the agent to treat search results as untrusted data or use specific delimiters.
- Capability inventory: The agent has the ability to perform network operations and modify repository state via
gh issue create(SKILL.md). - Sanitization: Absent; no validation or filtering of the external issue data is described.
Audit Metadata