skills/hcaiano/skills/ask-peer/Gen Agent Trust Hub

ask-peer

Fail

Audited by Gen Agent Trust Hub on Oct 6, 2026

Risk Level: HIGHPRIVILEGE_ESCALATIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
  • [PRIVILEGE_ESCALATION]: The skill instructs the agent to intentionally bypass safety controls and user-approval mechanisms.
  • Evidence in references/ask-claude.md: Instructs the use of --permission-mode bypassPermissions for write tasks, which disables the platform's requirement for user confirmation before executing actions.
  • Evidence in references/ask-codex.md: Instructs the use of -s danger-full-access combined with -c 'approval_policy="never"', which grants the peer agent unrestricted access without requiring user review for its operations.
  • [COMMAND_EXECUTION]: The skill relies on the execution of shell commands through the claude and codex CLI tools.
  • Evidence in references/ask-claude.md and references/ask-codex.md: Commands use subprocess-style execution to pass the workspace context, model configuration, and user-supplied prompts to the external CLIs.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a high-risk attack surface by forwarding unvalidated user input to peer agents running with the aforementioned elevated privileges.
  • Ingestion points: The argument-hint in SKILL.md captures user-provided questions or tasks.
  • Boundary markers: The bash templates in the reference files do not implement prompt delimiters or instructions to ignore embedded commands within the user input.
  • Capability inventory: The peer agents are granted Read, Grep, Glob access by default and full write access (bypassPermissions/danger-full-access) when implementation is requested.
  • Sanitization: No sanitization or validation is performed on the prompt content ($P) before it is piped to the peer CLIs.
  • [DATA_EXFILTRATION]: The skill facilitates the transfer of local project data to external model providers.
  • Evidence in SKILL.md: The 'Shared contract' mandates including the workspace root and relevant repository instructions in the external request.
  • Evidence in SKILL.md: The agent is instructed to read local configuration files, specifically ${CODEX_HOME:-$HOME/.codex}/config.toml, to extract model identifiers.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Oct 6, 2026, 11:16 PM