Security audit
Security checks for vulnerabilities and agentic risk
This skill is a disclosed B2B factory-search helper that sends the user's manufacturer-search terms to a documented external search API and returns public supplier profile information.
Install this only if you are comfortable sending factory-search queries and filters to the documented external B2B search service. Use it for manufacturer sourcing, not purchasing or price comparison, and keep host permissions limited to running the bundled lookup script.
The skill instructs the agent to execute a shell script (bash scripts/search.sh ...) but does not declare any explicit tool scope such as allowed tools or permissions. This creates a governance gap: an orchestrator may permit shell access more broadly than intended, increasing the chance of unintended command execution or misuse if the skill is invoked in the wrong context.
The trigger list includes broad natural-language phrases like '找厂家' and '谁家能代工', which can match many ordinary conversations and cause the skill to activate unexpectedly. Over-broad activation is dangerous because this skill has shell-backed behavior; unintended invocation could launch external queries, consume resources, or steer a conversation into the wrong tool path without clear user intent.
The file is entirely written as mandatory behavioral policy for the shared skill set and does not offer any user choice of language or locale. Because this shared guidance governs multiple skills, it implies a Chinese-language operating constraint without explicit opt-in or a documented justification that the skills are region- or language-specific.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
curl -s -X POST "https://gwgp-zmtc8kkxxzw.i.bdcloudapi.com/skill_api/factory_search" \
-H "Content-Type: application/json" \
-H "X-App-Source: workbuddy" \
-d '{"query":"铝合金压铸件 定制加工","location":"江苏苏州","page_size":10}'
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
[ -n "$WITH_PRODUCTS" ] && BODY="$BODY,\"with_products\":$WITH_PRODUCTS"
BODY="$BODY}"
RESP="$(curl -sS --max-time "$TIMEOUT" -X POST "$BASE_URL/skill_api/factory_search" \
-H "Content-Type: application/json" \
-H "X-App-Source: $APP_SOURCE" \
-d "$BODY" 2>&1)" || {
The routing guidance says to hand off some requests to a product-search skill, but the boundaries remain somewhat subjective ('买现货、比价格' vs. manufacturer search), which can lead to inconsistent or incorrect skill selection. In this case the danger is mainly operational: misrouting can trigger shell-based lookups unnecessarily, return irrelevant results, or bypass the better-scoped skill for the user's actual task.
No suspicious patterns detected.