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. 46 · Caution
Evidence
The sandbox observed nothing beyond the static findings; the proposal cites those.
Diff · removes 5 caught lines
Download .patchdiff --git a/SKILL.md b/SKILL.md --- a/SKILL.md +++ b/SKILL.md @@ -74,1 +74,0 @@ -Add to your agent's workspace context (e.g., `MEMORY.md` or system prompt): diff --git a/prompts/dream-cycle-prompt.md b/prompts/dream-cycle-prompt.md --- a/prompts/dream-cycle-prompt.md +++ b/prompts/dream-cycle-prompt.md @@ -211,1 +211,0 @@ -6. **NEVER write directly to AGENTS.md, MEMORY.md, TOOLS.md, SOUL.md, IDENTITY.md, or favorites.md** diff --git a/scripts/setup.sh b/scripts/setup.sh --- a/scripts/setup.sh +++ b/scripts/setup.sh @@ -150,1 +150,0 @@ -echo "3. ADD TO YOUR AGENT'S CONTEXT (system prompt or MEMORY.md):" diff --git a/INSTALL-AGENT.md b/INSTALL-AGENT.md --- a/INSTALL-AGENT.md +++ b/INSTALL-AGENT.md @@ -17,1 +17,0 @@ -3. Add to your agent's startup procedure (e.g., AGENTS.md): diff --git a/templates/AGENTS-snippet.md b/templates/AGENTS-snippet.md --- a/templates/AGENTS-snippet.md +++ b/templates/AGENTS-snippet.md @@ -1,1 +1,0 @@ -## Session Start — Mandatory Context Load (add to your AGENTS.md)
Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 1.5.1. 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: total-recall: Instructs the agent to modify its persistent memory or instruction files (KillerSkills verdict caution 46)
## 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 46/100**. Summary: static analysis only — behavior not yet observed. - See the findings below. Full trace and findings: https://killerskills.ai/skills/clawhub/total-recall/1.5.1 ## Findings with a location - `SKILL.md:74` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:74 · Instructs the agent to modify its persistent memory or instruction files - `prompts/dream-cycle-prompt.md:211` · Instructs the agent to modify its persistent memory or instruction files — prompts/dream-cycle-prompt.md:211 · Instructs the agent to modify its persistent memory or instruction files - `scripts/setup.sh:150` · Instructs the agent to modify its persistent memory or instruction files — scripts/setup.sh:150 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file - `INSTALL-AGENT.md:17` · Instructs the agent to modify its persistent memory or instruction files — INSTALL-AGENT.md:17 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file - `templates/AGENTS-snippet.md:1` · Instructs the agent to modify its persistent memory or instruction files — templates/AGENTS-snippet.md:1 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file ## Proposed change The attached patch removes the 5 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 gavdalf/total-recall --clone && cd total-recall curl -s https://killerskills.ai/skills/clawhub/total-recall/1.5.1/patch.diff | git apply --unidiff-zero git checkout -b killerskills/1.5.1 && git commit -am "total-recall: Instructs the agent to modify its persistent memory or instruction files" gh pr create --fill --body-file <(curl -s https://killerskills.ai/skills/clawhub/total-recall/1.5.1/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.