Is posthog:llma-cc-ingest safe to install?

SaferSkills independently audited posthog:llma-cc-ingest (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.

CategoryWeightCategory scoreContribution

Securityprompt, exec, net, exfil, eval

35%

100

35.0 pts

Supply chainhash, typosquat, maintainer, lockfile

20%

100

20.0 pts

Maintenancestaleness, pinning, CI

15%

100

15.0 pts

TransparencySKILL.md, perms, README

15%

100

15.0 pts

Communityinstalls, verify, response

15%

100

15.0 pts

Findings & checks · 0 flagged

Securityscore 100 · 0 findings

✓—All security checks passedNo findings in this category for the latest scan.pass

Supply chainscore 100 · 0 findings

✓—All supply chain checks passedNo findings in this category for the latest scan.pass

Maintenancescore 100 · 0 findings

✓—All maintenance checks passedNo findings in this category for the latest scan.pass

Transparencyscore 100 · 0 findings

✓—All transparency checks passedNo findings in this category for the latest scan.pass

Communityscore 100 · 0 findings

✓—All community checks passedNo findings in this category for the latest scan.pass

The primary manifest — the file an agent reads to learn what this artifact does.

claude-code/plugins/claude-plugins-official__posthog/commands/llma-cc-ingest/SKILL.md · 1 file

claude-code/plugins/claude-plugins-official__posthog/commands/llma-cc-ingest/SKILL.md0.9 KB · Markdown

name: posthog:llma-cc-ingest

description: Manually send a Claude Code session log to PostHog LLM Analytics

argument-hint: [session-id or path]

allowed-tools: Bash(python3:*),Bash(ls:*),Bash(echo:*)

LLM Analytics — Ingest Session

Manually send a Claude Code session log to PostHog LLM Analytics.

Usage

The argument $ARGUMENTS can be:

A session ID (e.g. 14a1687c-1937-4719-921d-cb2400d7a114)
A path to a JSONL file (e.g. ~/.claude/projects/-Users-me-myproject/14a1687c.jsonl)
Empty — will use the most recent session log for the current project

Steps

Resolve the session log path from the argument
Run the ingest script
Report the results

python3 ${CLAUDE_PLUGIN_ROOT}/scripts/llma_cc_ingest.py $ARGUMENTS

If no argument is provided, list recent sessions and let the user choose:

python3 ${CLAUDE_PLUGIN_ROOT}/scripts/llma_cc_ingest.py --list

posthog:llma-cc-ingest— agent skill

Is posthog:llma-cc-ingest safe to install?

LLM Analytics — Ingest Session

Usage

Steps

Audit the pieces. Scan the whole. Decide.