collaborate@1.0.3
CAUTION· static onlyPublisher claims: "Structures collaboration: picks the counterpart, runs a bounded exchange on a plan or decision, lands a decision or a recorded disagreement. Use when a plan needs critique, red-teaming, or a devil's advocate before commitment, when giving or asking for a second opinion, design review, or feedback on a draft, when a review thread keeps looping without anyone changing position, when a group review or pairing session needs structure, or when choosing between collaborating, delegating, and working solo. Not for routing specified work to sub-agents — that is delegation." Observed in sandbox: static analysis only — behavior not yet observed.
Coverage
Static only; nothing was run yet.The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.
Is [email protected] safe to install?
KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-10 and scored it 69/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Summary: static analysis only — behavior not yet observed.
Behavior trace
Queued for honeypot run · static analysis onlyThis version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.
Static findings
…didates that lose anyway. ## Budget Interaction The exchange budget (SKILL.md Rule 3: `budget_share`, default 10%, floor 5 min, cap 30 min) prices the routing decisi…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.| Untested assumptions | Adversarial reviewer | The 3 assumptions that, if false, kill the plan; not the wording |Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.| Confident plan, never attacked | Adversarial round: 1 counterpart attacks the 3 assumptions that, if false, kill the plan (`adversarial-review.md`) |Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.…ite your position before exposure.** One paragraph: decision, strongest reason, kill condition (what would change your mind). No kill condition = you want validation…Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.1. **Position first.** Decision + strongest reason + kill condition, written before the counterpart sees anything (Rule 5).Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.
What would make this Verified
11 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim ivangdavila: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.