Agency Agents Wrapper
v1.0.0Activate specialized AI agent personas across 18+ domains with tailored expertise, workflows, communication styles, and technical deliverables.
⭐ 0· 53·0 current·0 all-time
byJabir Iliyas Suraj-Deen@jabir-srj
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
Capability signals
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
OpenClaw
Benign
high confidencePurpose & Capability
Name/description promise (activate pre-built agent personas) matches the bundle: the repository contains many .md persona files organized by domain and the SKILL.md tells the agent to list/read those files. There are no unrelated environment variables, binaries, or config paths required.
Instruction Scope
SKILL.md only instructs the agent to browse and read local markdown persona files (e.g., ls and open references/agents/...). It does not direct the agent to read system files, access external endpoints, collect or transmit user secrets, or run arbitrary commands beyond listing/reading these repository files.
Install Mechanism
No install spec is present (instruction-only), which is lowest-risk. There is one shell script file present (references/agents/integrations/mcp-memory/setup.sh) but SKILL.md does not instruct running it. Presence of that script is plausible for an integrations subfolder and is not by itself evidence of an installer or remote download.
Credentials
The skill declares no required environment variables, no primary credential, and no config paths. Nothing in SKILL.md tries to access undeclared env vars or credentials.
Persistence & Privilege
Flags show always:false and normal model invocation; the skill does not request permanent presence or system-wide configuration changes in its instructions. Nothing in the files indicates modification of other skills or system settings.
Assessment
This package appears coherent for the stated purpose (a local collection of agent/persona files). Before enabling: (1) inspect the one included shell script (references/agents/integrations/mcp-memory/setup.sh) — do not run it unless you trust its contents, (2) confirm the skill's origin since registry metadata lists 'unknown' and there's no homepage, and (3) remember that although the skill itself requests no secrets, personas may ask you for context during use; don't paste sensitive credentials into chats. If you want extra caution, open the repository files yourself and verify there are no embedded external endpoints or secret-collection prompts in the persona MDs before use.Like a lobster shell, security has layers — review code before you run it.
latestvk976twj1xxb4b8wrhck173k81584e9s2
License
MIT-0
Free to use, modify, and redistribute. No attribution required.