slack-message-formatter
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill converts user-supplied Markdown content into HTML and mrkdwn, which can allow malicious instructions within the input to influence the agent's behavior during the conversion process.
- Ingestion points: User-provided Markdown content processed through prompts (SKILL.md).
- Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands in the source text.
- Capability inventory: The skill performs file writes to /tmp, modifies the system clipboard, opens the web browser, and sends network requests.
- Sanitization: No sanitization or escaping of the user-provided Markdown is documented.
- [DATA_EXFILTRATION]: The skill sends formatted message content to an external endpoint via the CCH_SLA_WEBHOOK environment variable.
- [COMMAND_EXECUTION]: The skill automates system-level actions including copying content to the clipboard and opening generated HTML files in a browser, which involves the execution of system commands by the agent.
Audit Metadata