Skills
Navigate
skills/aisa-team/agent-skills/aisa-twitter-post-engage/Gen Agent Trust Hub

aisa-twitter-post-engage

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from Twitter search results and profiles, creating a surface for indirect prompt injection. Ingestion points include various read commands in scripts/twitter_client.py. Boundary markers are provided in references/engage_twitter.md to guide the agent in handling this data safely. Capabilities include posting and engagement actions via the AIsa relay. Sanitization is not explicitly defined in the local scripts but is managed by the relay service.
  • [COMMAND_EXECUTION]: The skill executes local Python scripts to facilitate communication with the AIsa API. These scripts are purpose-built for the skill's documented tasks and do not involve arbitrary command execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 02:35 AM