service-de-waba-integrate
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the
echocommand to write a JSON response to a local temporary file (/tmp/linking-waba-result.json). This is used to pass the result of the user interaction back to the calling orchestrator or subsequent skills.- [INDIRECT_PROMPT_INJECTION]: The skill interpolates external input variables{WABA_ID}and{SF_BM_ID}directly into the Markdown text rendered to the user. - Ingestion points: Input variables defined in the frontmatter and used in the Stage 1 rendering template of
SKILL.md. - Boundary markers: No explicit delimiters or instructions are used to wall off the interpolated variables from the rest of the instructional prompt.
- Capability inventory: The skill possesses the capability to write to the local filesystem using shell commands.
- Sanitization: There is no evidence of input validation or escaping for the
{WABA_ID}or{SF_BM_ID}fields before they are displayed to the user.
Audit Metadata