twitter-engager
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to the handling of external data combined with powerful tool access.
- Ingestion points: The agent is instructed to monitor and respond to Twitter mentions, direct messages (DMs), and trending topics (SKILL.md, Phase 3).
- Boundary markers: Absent. There are no instructions or delimiters provided to help the agent distinguish between its own instructions and potentially malicious commands embedded in external content.
- Capability inventory: The skill explicitly grants the agent access to
bash,git, andFile ops(SKILL.md, Copilot CLI Operations section). - Sanitization: Absent. There is no mention of input validation, escaping, or filtering for content retrieved from external sources.
- [COMMAND_EXECUTION]: The skill provides the agent with access to the
bashtool to execute commands and run tests. - Evidence: The 'Copilot CLI Operations' section in SKILL.md authorizes the use of
bashfor executing commands. While this is a standard tool in this environment, its presence increases the impact of any successful prompt injection.
Audit Metadata