community-hottopic-insight

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through its data processing workflow. \n
  • Ingestion points: The agent is instructed to fetch and process full text and comments from community posts using the ae-cli community +search_posts and +get_post_detail commands in SKILL.md. \n
  • Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following instructions that may be embedded within the external post content. \n
  • Capability inventory: The skill allows the agent to execute shell commands via the ae-cli toolset, providing a path for potential exploitation if malicious instructions are successfully injected. \n
  • Sanitization: The instructions do not define any filtering or sanitization steps for the retrieved external content before it is processed or summarized. \n- [COMMAND_EXECUTION]: The skill's core workflow in SKILL.md involves the construction of shell commands (ae-cli community +search_posts) using variables derived from user input, such as the <topic title> used in the --search-word argument. This represents a potential command injection surface if the input is not correctly escaped or validated by the underlying execution environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 10:17 AM
Security Audit — agent-trust-hub — community-hottopic-insight