gm-orchestrate
Pass
Audited by Gen Agent Trust Hub on Oct 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill demonstrates a vulnerability surface for indirect prompt injection by ingesting and acting upon untrusted data from external CI logs.
- Ingestion points: CI job logs retrieved through the
ci_logtool and file content from the repository. - Boundary markers: The instructions do not define delimiters or specific warnings to ignore embedded commands within the ingested text.
- Capability inventory: The skill possesses the ability to execute other skills (gm-prd, gm-hop), perform file writes via
fs_write, and interact with the GitHub API. - Sanitization: No explicit sanitization or validation of external content is mentioned before it influences subsequent agent turns.
- [COMMAND_EXECUTION]: The skill orchestrates the execution of various tools and subprocesses, including
ci_logand standard Git commands, to manage the repository state. - [DYNAMIC_EXECUTION]: The orchestrator dynamically constructs and dispatches calls to sub-skills (gm-prd and gm-hop) using arguments and payloads generated at runtime based on the status of work rows and graph nodes.
Audit Metadata