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. 71 · Caution
Evidence
The sandbox observed nothing beyond the static findings; the proposal cites those.
Diff · removes 3 caught lines
Download .patchdiff --git a/SKILL.md b/SKILL.md --- a/SKILL.md +++ b/SKILL.md @@ -91,1 +91,0 @@ -2. Update workspace `MEMORY.md` with a managed constitution index block: diff --git a/skill-card.md b/skill-card.md --- a/skill-card.md +++ b/skill-card.md @@ -28,1 +28,0 @@ -Risk: The skill can create or synchronize AGENT_CONSTITUTION.md and update a workspace MEMORY.md constitution index, which may affect future agent behavior. @@ -50,1 +49,0 @@ -**Other Properties Related to Output:** [May create or update registry JSON, AGENT_CONSTITUTION.md, and a managed MEMORY.md constitution index when initialized.]
Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 0.2.2. 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: reed-agent-network: Instructs the agent to modify its persistent memory or instruction files (KillerSkills verdict caution 71)
## 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 71/100**. Summary: static analysis only — behavior not yet observed. - See the findings below. Full trace and findings: https://killerskills.ai/skills/clawhub/reed-agent-network/0.2.2 ## Findings with a location - `SKILL.md:91` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:91 · Instructs the agent to modify its persistent memory or instruction files - `skill-card.md:50` · Instructs the agent to modify its persistent memory or instruction files — skill-card.md:50 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file - `skill-card.md:28` · Instructs the agent to modify its persistent memory or instruction files — skill-card.md:28 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file ## Proposed change The attached patch removes the 3 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.