Propose a patch
A fix the maintainer can act on, with the evidence attached. It opens under your GitHub account in your browser; KillerSkills holds no token and never modifies the package. The fix is verified the only way we verify anything: the next crawl re-runs the new version in the honeypot. 58 · Caution
Evidence
The sandbox observed nothing beyond the static findings; the proposal cites those.
Diff · removes 6 caught lines
Download .patchdiff --git a/resources/prompts/prompts.md b/resources/prompts/prompts.md
--- a/resources/prompts/prompts.md
+++ b/resources/prompts/prompts.md
@@ -119,1 +119,0 @@
-**角色定义**
@@ -120,1 +119,0 @@
-你是专业的招标要求抽取内容校验专家,精通招标文本抽取规则与合规性判定逻辑,核心职责是对照包含 "检查内容"、"检查方法"、"判定标准" 的检查清单,逐一项验证已抽取内容是否符合要求,且仅筛选并输出 “不符合” 的检查项,不呈现其他结果。
@@ -122,1 +120,0 @@
-**核心任务**
@@ -123,1 +120,0 @@
-严格遵循检查清单的校验规则,对已抽取的招标要求内容进行精准验证,最终仅输出判定为 “不符合” 的检查项,确保:① 不遗漏任何 “不符合” 项;② 不包含 “符合”“无抽取内容” 的检查项;③ 结果格式严格统一;④ 问题描述精准明确。
@@ -125,1 +121,0 @@
-**重要规则(强化筛选与约束)**
diff --git a/scripts/tender_parse.py b/scripts/tender_parse.py
--- a/scripts/tender_parse.py
+++ b/scripts/tender_parse.py
@@ -81,1 +81,0 @@
-raise ValueError("LLM API key is required. Please set LLM_API_KEY environment variable or pass api_key parameter.")
Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 1.0.9. If the behavior is intended, declare it (host under permissions.network, a line in the README) instead of removing it; the next crawl scores declarations.
Issue / PR body
Title: ai-tender: Hidden zero-width characters detected (KillerSkills verdict caution 58)
## What the honeypot observed KillerSkills ran **[email protected]** in an isolated sandbox (decoy credentials, recording proxy, syscall trace; engine 1.9.2) and scored it **CAUTION 58/100**. Summary: static analysis only — behavior not yet observed. - See the findings below. Full trace and findings: https://killerskills.ai/skills/clawhub/ai-tender/1.0.9 ## Findings with a location - `resources/prompts/prompts.md:119` · Hidden zero-width characters detected — resources/prompts/prompts.md:119 · Hidden zero-width characters detected — may conceal content - `resources/prompts/prompts.md:120` · Hidden zero-width characters detected — resources/prompts/prompts.md:120 · Hidden zero-width characters detected — may conceal content - `scripts/tender_parse.py:81` · Credential pass-through configuration — scripts/tender_parse.py:81 · Credential pass-through configuration — agent relays sensitive credentials - `resources/prompts/prompts.md:123` · Hidden zero-width characters detected — resources/prompts/prompts.md:123 · Hidden zero-width characters detected — may conceal content - `resources/prompts/prompts.md:122` · Hidden zero-width characters detected — resources/prompts/prompts.md:122 · Hidden zero-width characters detected — may conceal content - `resources/prompts/prompts.md:125` · Hidden zero-width characters detected — resources/prompts/prompts.md:125 · Hidden zero-width characters detected — may conceal content ## Proposed change The attached patch removes the 6 lines above. If the behavior is intended, the fix is to declare it instead: list the host under `permissions.network` (or the MCP manifest) and say in the README why the package needs it; the next crawl will re-score it with the declaration taken into account. ## How this will be verified Nothing is "verified safe" by assertion. When a new version is published, KillerSkills re-runs it in the honeypot and the verdict page updates; you can trigger it early from the verdict page ("Re-scan after I publish a fix"). Reply here or at [email protected] if you believe the verdict is wrong; disputes are reviewed by a person and the outcome is published on the verdict page. _Proposed through killerskills.ai/threats by a user of the package, under their own GitHub account. The evidence is public; the package was never modified by KillerSkills._
We count proposals opened, not merged: a merge shows up as a new version that the crawl re-runs. Disputes: the maintainer can contest the verdict from its page; a person reviews it and the outcome is published.