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. 78 · Caution

Evidence

The sandbox observed nothing beyond the static findings; the proposal cites those.

Diff · removes 5 caught lines

Download .patch

diff --git a/skills/agentsop-conventions-pinning/SKILL.md b/skills/agentsop-conventions-pinning/SKILL.md
--- a/skills/agentsop-conventions-pinning/SKILL.md
+++ b/skills/agentsop-conventions-pinning/SKILL.md
@@ -408,1 +408,0 @@
-…text threshold (whole context, not just rules) [aider.chat/docs/troubleshooting/edit-errors.html] | < 200 lines per CLAUDE.md recommended; full file loaded regardless [code.claude.com/docs/en/memory] | < 5…
diff --git a/skills/agentsop-conventions-pinning/references/R1-source-evidence.md b/skills/agentsop-conventions-pinning/references/R1-source-evidence.md
--- a/skills/agentsop-conventions-pinning/references/R1-source-evidence.md
+++ b/skills/agentsop-conventions-pinning/references/R1-source-evidence.md
@@ -93,1 +93,0 @@
-## Claim 7: When to add to CLAUDE.md
@@ -97,1 +96,0 @@
-> "Treat CLAUDE.md as the place you write down what you'd otherwise re-explain. Add to it when:
diff --git a/skills/agentsop-conventions-pinning/references/R2-tool-equivalents.md b/skills/agentsop-conventions-pinning/references/R2-tool-equivalents.md
--- a/skills/agentsop-conventions-pinning/references/R2-tool-equivalents.md
+++ b/skills/agentsop-conventions-pinning/references/R2-tool-equivalents.md
@@ -223,1 +223,0 @@
-- **Cross-machine personal preferences**. CLAUDE.local.md is local to its directory; if you have 5 worktrees, you write it 5 times. Workaround: `@~/.claude/my-prefs.md` import in CLAUDE.md.
diff --git a/skills/agentsop-conventions-pinning/intermediate/operation_candidates.json b/skills/agentsop-conventions-pinning/intermediate/operation_candidates.json
--- a/skills/agentsop-conventions-pinning/intermediate/operation_candidates.json
+++ b/skills/agentsop-conventions-pinning/intermediate/operation_candidates.json
@@ -38,1 +38,0 @@
-… "trigger": "Conventions file written", "action": "Per tool: Aider -> add `read: CONVENTIONS.md` to `.aider.conf.yml`; Claude Code -> place at `./CLAUDE.md` or `./.claude/CLAUDE.md` (auto-loaded); Cursor -> add `.cursor/rules/main.mdc`…

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 0.1.3. 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: skillalchemy: Instructs the agent to modify its persistent memory or instruction files (KillerSkills verdict caution 78)

## 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 78/100**. Summary: no network, touches nothing outside the project, writes no memory.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/clawhub/skillalchemy/0.1.3

## Findings with a location
- `skills/agentsop-conventions-pinning/SKILL.md:408` · Instructs the agent to modify its persistent memory or instruction files — skills/agentsop-conventions-pinning/SKILL.md:408 · Instructs the agent to modify its persistent memory or instruction files
- `skills/agentsop-conventions-pinning/references/R1-source-evidence.md:93` · Instructs the agent to modify its persistent memory or instruction files — skills/agentsop-conventions-pinning/references/R1-source-evidence.md:93 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `skills/agentsop-conventions-pinning/references/R2-tool-equivalents.md:223` · Instructs the agent to modify its persistent memory or instruction files — skills/agentsop-conventions-pinning/references/R2-tool-equivalents.md:223 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `skills/agentsop-conventions-pinning/references/R1-source-evidence.md:97` · Instructs the agent to modify its persistent memory or instruction files — skills/agentsop-conventions-pinning/references/R1-source-evidence.md:97 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `skills/agentsop-conventions-pinning/intermediate/operation_candidates.json:38` · Instructs the agent to modify its persistent memory or instruction files — skills/agentsop-conventions-pinning/intermediate/operation_candidates.json:38 · 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._

Open the issue on GitHub (agentsope/SkillAlchemy)Fork to open a PR

# or from a terminal, under your own account:
gh repo fork agentsope/SkillAlchemy --clone && cd SkillAlchemy
curl -s https://killerskills.ai/skills/clawhub/skillalchemy/0.1.3/patch.diff | git apply --unidiff-zero
git checkout -b killerskills/0.1.3 && git commit -am "skillalchemy: Instructs the agent to modify its persistent memory or instruction files"
gh pr create --fill --body-file <(curl -s https://killerskills.ai/skills/clawhub/skillalchemy/0.1.3/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.