Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Apollo Planning
v1.1.0拆解大任务为多步小操作（每步数分钟），提供精确文件路径、代码和测试命令的详细实现计划。
⭐ 0· 37·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
medium confidencePurpose & Capability
Name, description and SKILL.md all align: the skill's goal is to produce step-by-step implementation plans including exact file paths, test commands and git steps. Nothing requested (no env vars, no binaries) contradicts that stated purpose.
Instruction Scope
SKILL.md tells the agent to produce exact file paths, test code, and to run/git commit/merge and pytest commands; it also recommends dispatching subagents (apollo-subagent-dev) and assumes a working directory created by a 'brainstorming' skill. These are in-scope for a planning skill, but the document presumes repository read/write access and other skills without declaring them. The plan's requirement to include runnable code/tests and specific git steps implies the agent or subagents may be expected to execute commands or produce changes — the skill does not explicitly limit or describe those execution privileges.
Install Mechanism
Instruction-only skill (no install spec, no code files). This is lowest-risk from an install-execution perspective; nothing will be downloaded or written by an installer.
Credentials
The SKILL.md expects actions that typically require credentials and filesystem access (git commit/merge, creating/modifying files in repo, running tests). Yet the registry metadata declares no required env vars, no config paths and no primary credential. The skill also references other skills (apollo-subagent-dev, apollo-finishing-branch) but does not declare them as dependencies. Absence of any declared credential requirements is disproportionate to the implied need for repository write/push permissions or for subagent capabilities.
Persistence & Privilege
always is false and disable-model-invocation is default (agent may invoke autonomously). There is no request to modify other skills or system-wide settings. Be aware that autonomous invocation combined with implicit repo-write actions increases risk, but autonomy alone is expected behavior and not flagged here.
What to consider before installing
This skill appears to do what it says (produce detailed, small-step implementation plans), but exercise caution before enabling it with write/execute permissions. Things to check before installing:
- Confirm the skill owner and origin: _meta.json in the package contains a different ownerId/slug/version than the registry metadata—ask the publisher to explain the mismatch or provide a trusted homepage/source.
- Understand repository access: the plan templates include git commits, merges, file creation/modification and running tests. The skill does not declare credentials, but in practice executing these steps requires repo credentials and filesystem access. If you plan to let the agent act on plans, restrict it to a sandbox or read-only mode until you review outputs.
- Missing dependency declarations: the SKILL.md recommends subagents (apollo-subagent-dev) and a brainstorming skill; verify those components exist and are trustworthy before enabling automated dispatch.
- Review outputs before execution: because the plan includes exact code and git commands, always review the generated plan and any code before allowing commits or merges. Consider running plans in an isolated branch and CI pipeline rather than giving the agent direct push/merge rights.
- If you lack confidence in the publisher, keep the skill user-invocable only and do not grant it any secrets or direct repository write access. Request source/homepage or signed provenance from the publisher if you want to run it with elevated privileges.Like a lobster shell, security has layers — review code before you run it.
latestvk97c8fkdwheskc8cqztkh4ar0x84aqyx
License
MIT-0
Free to use, modify, and redistribute. No attribution required.