dispatching-parallel-agents — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited dispatching-parallel-agents (Agent Skill) and scored it 45/100 (orange). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 2 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 2 flagged
A base64 string of 128+ characters appears in a documentation file. Encoded prompt injection hides the hostile instruction in base64 — invisible to keyword filters — and relies on the agent's ability to decode it at runtime. There is no normal authoring reason to embed a multi-hundred-byte base64 blob in skill docs.
*.sig, SIGNATURES) outside the documentation.A base64 string of 128+ characters appears in a documentation file. Encoded prompt injection hides the hostile instruction in base64 — invisible to keyword filters — and relies on the agent's ability to decode it at runtime. There is no normal authoring reason to embed a multi-hundred-byte base64 blob in skill docs.
*.sig, SIGNATURES) outside the documentation.Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Use parallel children for two or more ad-hoc, bounded tasks only when their independence is already credible and concurrency is worth the coordination. Parallelism changes elapsed time; it does not relax evidence, ownership, or completion requirements.
Dispatch only when all are true:
2+ distinct tasks or evidence questions;Keep work inline when decomposition is still exploratory, failures may share a root cause, full-system context is required, or tasks are too small to repay the handoff. A written implementation plan routes to aegis:subagent-driven-development, not this ad-hoc workflow.
Choose the live host's context inheritance mode deliberately. Give each child the minimum sufficient instructions and evidence; do not rely on accidental inheritance or assume that context must never be inherited.
Each task packet states:
Isolated model context does not imply an isolated filesystem, process, Git repository, credential, rate limit, or external service. Prefer read-only investigation. If children may edit, assign disjoint write ownership explicitly. The coordinator owns staging, commits, branches, worktrees, integration, and other Git lifecycle mutations.
limits.
visible workspace changes.
parallel mutation and return the work to one owner.
For read-only work, validate the synthesis against the cited sources.
The coordinator owns the concurrency budget. Children do not delegate recursively unless their packet explicitly permits it. A failed, cancelled, or timed-out child contributes any available partial evidence; otherwise record no result and the unresolved unknowns. Retry only with a materially different packet or serialize the task.
Child output is evidence or a proposal, not a GateDecision, completion authority, or permission for external action.
state.
When any of these appears, narrow the packets, serialize the shared portion, or return to the owning debugging or plan workflow.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.