coral
Pass
Audited by Gen Agent Trust Hub on May 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
coral sqlCLI tool to execute queries. This command execution is the primary mechanism for the skill's intended functionality of data retrieval. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it retrieves and processes data from external, potentially attacker-controlled sources (e.g., GitHub, Slack, Linear, Datadog, Sentry).
- Ingestion points: External data is ingested into the agent's context through queries executed against various schemas and table functions in
SKILL.md. - Boundary markers: The instructions do not provide boundary markers or delimiters to separate the untrusted data from the system instructions.
- Capability inventory: The skill has the capability to execute shell commands using the
coralCLI. - Sanitization: No sanitization, escaping, or validation of the retrieved data is mentioned before it is processed by the agent.
Audit Metadata