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. 63 · Caution
Evidence
The sandbox observed nothing beyond the static findings; the proposal cites those.
Diff · removes 9 caught lines
Download .patchdiff --git a/references/subagent-definitions.md b/references/subagent-definitions.md --- a/references/subagent-definitions.md +++ b/references/subagent-definitions.md @@ -205,1 +205,0 @@ -4. Update Post Performance Log in memory.md @@ -211,1 +210,0 @@ -4. Update Competitor Watchlist in memory.md @@ -216,1 +214,0 @@ -3. Update Audience Intelligence in memory.md @@ -227,1 +224,0 @@ -- Log the update with date and findings in memory.md diff --git a/SKILL.md b/SKILL.md --- a/SKILL.md +++ b/SKILL.md @@ -35,1 +35,0 @@ -8. **Update memory after every session** — Append to [memory.md](references/memory.md). Never delete old entries. @@ -50,1 +49,0 @@ -- If authenticated -> update memory.md Environment Status to `twitter-cli: installed` @@ -202,1 +200,0 @@ -| **x-intel-updater** (yellow) | Analyze performance, update strategy files | memory.md, content-strategy.md, hook-library.md | @@ -243,1 +240,0 @@ -4. Update [memory.md](references/memory.md) Post Performance Log with fresh data @@ -542,1 +538,0 @@ -5. Update Post Performance Log in [memory.md](references/memory.md)
Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 1.0.0. 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: x-social-manager-dist: Instructs the agent to modify its persistent memory or instruction files (KillerSkills verdict caution 63)
## What the honeypot observed KillerSkills ran **[email protected]** in an isolated sandbox (decoy credentials, recording proxy, syscall trace; engine 1.8.1) and scored it **CAUTION 63/100**. Summary: static analysis only — behavior not yet observed. - See the findings below. Full trace and findings: https://killerskills.ai/skills/clawhub/x-social-manager-dist/1.0.0 ## Findings with a location - `references/subagent-definitions.md:227` · Instructs the agent to modify its persistent memory or instruction files — references/subagent-definitions.md:227 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file - `references/subagent-definitions.md:205` · Instructs the agent to modify its persistent memory or instruction files — references/subagent-definitions.md:205 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file - `references/subagent-definitions.md:211` · Instructs the agent to modify its persistent memory or instruction files — references/subagent-definitions.md:211 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file - `SKILL.md:35` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:35 · Instructs the agent to modify its persistent memory or instruction files - `SKILL.md:202` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:202 · Instructs the agent to modify its persistent memory or instruction files - `SKILL.md:243` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:243 · Instructs the agent to modify its persistent memory or instruction files - `SKILL.md:50` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:50 · Instructs the agent to modify its persistent memory or instruction files - `SKILL.md:542` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:542 · Instructs the agent to modify its persistent memory or instruction files - `references/subagent-definitions.md:216` · Instructs the agent to modify its persistent memory or instruction files — references/subagent-definitions.md:216 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file ## Proposed change The attached patch removes the 9 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._
# or from a terminal, under your own account: gh repo fork rabden/X-twitter-social-manager-skill --clone && cd X-twitter-social-manager-skill curl -s https://killerskills.ai/skills/clawhub/x-social-manager-dist/1.0.0/patch.diff | git apply --unidiff-zero git checkout -b killerskills/1.0.0 && git commit -am "x-social-manager-dist: Instructs the agent to modify its persistent memory or instruction files" gh pr create --fill --body-file <(curl -s https://killerskills.ai/skills/clawhub/x-social-manager-dist/1.0.0/patch.md)
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.