silent-failure-hunter
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests arbitrary task context, scope, and issue/PR details from the user or surrounding environment and passes it directly to the
codex-subagenttool. This presents a potential surface where malicious instructions embedded in the processed data could influence the subagent's behavior. - Ingestion points: Heredoc block in the bash execution command within
SKILL.md. - Boundary markers: None identified; user input is passed directly between EOF delimiters.
- Capability inventory: Executes the
codex-subagentCLI tool. - Sanitization: No sanitization or input validation logic is present in the instruction file.
- [COMMAND_EXECUTION]: The skill instructs the agent to execute the
codex-subagentcommand-line utility. This is the primary mechanism for the skill's functionality and does not involve elevated privileges or suspicious command chains.
Audit Metadata