service-de-headless-channel-configure
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
sfCLI tool to perform data queries (sf data query) and configuration tasks within the Salesforce environment. These operations have the potential to modify organizational metadata and process sensitive identifiers for messaging platforms like WhatsApp, LINE, and Facebook. - [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt or query injection by interpolating untrusted user inputs directly into SOQL query strings and command parameters.
- Ingestion points: User-provided inputs including
{PHONE_NUMBER_ID},{LINE_CHANNEL_ID},{APPLE_BC_ID}, and{PAGE_ID}as described inreferences/inputs.md. - Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the user-supplied identifiers before they are interpolated into queries in Stage 1.
- Capability inventory: The skill possesses significant capabilities, including the ability to query records, insert new messaging channels, and patch channel status to 'Active' through its lifecycle stages and related leaf skills.
- Sanitization: There is no evidence of input validation, escaping, or sanitization logic for these identifiers before they are used to construct dynamic queries or forwarded to downstream configuration tools.
Audit Metadata