cmd-gh-issue
Pass
Audited by Gen Agent Trust Hub on Apr 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
ghCLI to create issues by wrapping synthesized conversation content in a bash heredoc. If the conversation content contains the delimiterISSUE_EOFfollowed by shell-escape sequences, it could lead to arbitrary command execution within the agent's environment. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests untrusted data from the conversation history and interpolates it into instructions for shell-based tool usage.
- Ingestion points: The skill reads the entire conversation context to populate the issue body.
- Boundary markers: There are no explicit delimiters or instructions provided to the agent to prevent it from following commands or instructions embedded within the conversation data.
- Capability inventory: The skill is capable of executing arbitrary shell commands via the
ghCLI integration. - Sanitization: No evidence of sanitization or escaping is present in the instructions to ensure the synthesized content does not interfere with the shell command structure.
Audit Metadata