BC nonblocking-agent-execution
Enhanced Non-Blocking Agent Execution with AI-powered improvements. Prevents "agent stopped responding / stuck / no output" failures in sandboxed agent runtimes (Arena Agent Mode, OpenClaw, Codex) where a single long tool call blocks the turn and stdin is closed so interactive prompts hang forever. NEW in v2.0.0: - Full jobctl.sh implementation with all commands - Multi-model compatibility (OpenAI, Anthropic, Mistral, Groq, etc.) - Token usage optimization and monitoring - Hallucination reduction via verification - Self-improving through feedback loops - Comprehensive debugging and logging - Idempotent operations and graceful error handling - Watchdog timers for timeout protection - Callback URL support for async notifications - Durable state persistence across turns Provides the detach → bounded-poll → durable-state pattern plus a ready-to-use jobctl.sh runner with enhanced features for production use.
Enhanced Non-Blocking Agent Execution with AI-powered improvements.
As a process C 58/100 · Has gaps — weak spots: when it triggers, inputs and preconditions
The same skill appears in 1 more place: ClawHub
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 10
✓ No critical or high findings
Medium and low: 10
-
medium Exfiltration
exfil-webhook-urldocs/INTEGRATION.md:636Webhook / callback URL commonly used for exfiltration (verify the destination) (documentation of a security skill)Use a tool like [webhook.site](https://webhook.site) or [ngrok](https://ngrok.com) for testing.
security skill -
low Exfiltration
exfil-webhook-urldocs/INTEGRATION.md:646Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)./scripts/jobctl.sh start callback-test 'echo hello' http://your-ngrok-url.ngrok.io/callback
placeholder -
low Dangerous commands
cmd-background-processREADME.md:312Starts a background / autostarted process (documentation of a security skill)setsid nohup command > output.log 2> error.log &
security skill -
low Dangerous commands
cmd-background-processscripts/jobctl.sh:582Starts a background / autostarted process (code comment)# Start the job in background with setsid and nohup
comment -
low Dangerous commands
cmd-background-processscripts/jobctl.sh:612Starts a background / autostarted process (code comment)# Launch with setsid and nohup
comment -
low Dangerous commands
cmd-background-processscripts/jobctl.sh:613Starts a background / autostarted processsetsid nohup bash "$wrapper" > /dev/null 2>&1 &
-
low Dangerous commands
cmd-background-processSKILL.md:80Starts a background / autostarted process (documentation table row; documentation of a security skill)| **Blocking tool call** — one `bash` call runs 20 min | UI shows nothing, user aborts | Detach with `setsid nohup ... &` + watchdog timer |
tablesecurity skill -
low Dangerous commands
cmd-background-processSKILL.md:82Starts a background / autostarted process (documentation table row; documentation of a security skill)| **Aborted turn kills the child process** | Work silently lost, half-done state | Detach with `setsid`, persist state to disk + atomic writes |
tablesecurity skill -
low Dangerous commands
cmd-background-processSKILL.md:611Starts a background / autostarted process (documentation of a security skill)setsid nohup command > output.log 2> error.log &
security skill
A further 1 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5003 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "categories" - note
frontmatter-keyunknown frontmatter key "topics"
Process rating: all ten parameters 58/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 5003 tokens
- 85Steps. 110 steps, 2 vague phrases
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 17 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 916: 120–800 characters recommended
- -227 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +4Structure: 83 headings
- +3Step-by-step instructions: 110 items
- +3Output format is stated explicitly
- +4Has examples (35 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.