Propose a patch

Evidence

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

diff --git a/site/src/content/docs/reference/config.md b/site/src/content/docs/reference/config.md
--- a/site/src/content/docs/reference/config.md
+++ b/site/src/content/docs/reference/config.md
@@ -8,1 +8,0 @@
-Generated by scripts/gen-docs-reference.ts. Do not edit by hand; run `bun run docs:gen`.
diff --git a/site/src/content/docs/reference/cli.md b/site/src/content/docs/reference/cli.md
--- a/site/src/content/docs/reference/cli.md
+++ b/site/src/content/docs/reference/cli.md
@@ -8,1 +8,0 @@
-Generated by scripts/gen-docs-reference.ts. Do not edit by hand; run `bun run docs:gen`.
@@ -61,1 +60,0 @@
---claude-md             add the AI Task Tracking line to ~/.claude/CLAUDE.md; --no-claude-md to skip
@@ -75,1 +73,0 @@
-| `--claude-md` | add the AI Task Tracking line to ~/.claude/CLAUDE.md; --no-claude-md to skip |
diff --git a/src/setup/setup.ts b/src/setup/setup.ts
--- a/src/setup/setup.ts
+++ b/src/setup/setup.ts
@@ -86,1 +86,0 @@
---claude-md             add the AI Task Tracking line to ~/.claude/CLAUDE.md; --no-claude-md to skip
diff --git a/site/src/content/docs/start/first-run.md b/site/src/content/docs/start/first-run.md
--- a/site/src/content/docs/start/first-run.md
+++ b/site/src/content/docs/start/first-run.md
@@ -36,1 +36,0 @@
-| `--claude-md` | add the AI Task Tracking line to `~/.claude/CLAUDE.md`; `--no-claude-md` to skip |

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 0.1.0. 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: ai-task-tracking: HTML comment carrying imperative instructions to the agent (KillerSkills verdict caution 62)

## 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 62/100**. Summary: no network, touches nothing outside the project, writes no memory.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/glama/ai-task-tracking/0.1.0

## Findings with a location
- `site/src/content/docs/reference/config.md:8` · HTML comment carrying imperative instructions to the agent — site/src/content/docs/reference/config.md:8 · HTML comment carrying imperative instructions to the agent
- `site/src/content/docs/reference/cli.md:8` · HTML comment carrying imperative instructions to the agent — site/src/content/docs/reference/cli.md:8 · HTML comment carrying imperative instructions to the agent
- `site/src/content/docs/reference/cli.md:75` · Instructs the agent to modify its persistent memory or instruction files — site/src/content/docs/reference/cli.md:75 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `site/src/content/docs/reference/cli.md:61` · Instructs the agent to modify its persistent memory or instruction files — site/src/content/docs/reference/cli.md:61 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `src/setup/setup.ts:86` · Instructs the agent to modify its persistent memory or instruction files — src/setup/setup.ts:86 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `site/src/content/docs/start/first-run.md:36` · Instructs the agent to modify its persistent memory or instruction files — site/src/content/docs/start/first-run.md:36 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file

## Proposed change
The attached patch removes the 6 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._