para-second-brain
Verdict safe, but 1 finding (1 medium), mainly prompt injection. Most recent scan 2026-02-06.
The para-second-brain skill implements a PARA (Projects, Areas, Resources, Archive) organizational system for agent memory with a notable security concern around transitive trust. The core functionality (directory structure creation via setup.sh) is benign, but the symlink trick that makes the entire notes/ directory searchable via memory_search creates an indirect prompt injection risk (AITech-1.2). If users place untrusted content in their notes/ folders, the agent could discover and follow malicious instructions during search operations. The skill also has minor issues with missing optional metadata fields and incomplete documentation. No critical threats (data exfiltration, command injection, hardcoded secrets) were detected. The bash script uses safe practices (set -e, quoted variables, no eval/exec). Overall, this is a moderately safe skill with one medium-severity transitive trust concern that should be documented for users.
Scanner's overall assessment (LLM analyzer)
Second scanner: NVIDIA SkillSpector
SkillSpector found no issues but could not fully inspect the package, usually because SKILL.md refers to a file that is not present, so it fails closed to CAUTION instead of SAFE. Read it as "not fully checked", not as a finding. How the two scanners compare across the whole corpus: Two scanners, one corpus.
What this skill does
Organize your agent's knowledge using PARA (Projects, Areas, Resources, Archive) — then make it ALL searchable. The symlink trick enables full semantic search across your entire knowledge base, not just MEMORY.md. Includes session transcript indexing and memory flush protocol. Your agent finally has a real second brain.
- Package
- 7 files, 17 KB
- SKILL.md
- 1831 words, 12+ sections
- Code
- Shell (1)
- Version
- 2.0.1
SKILL.md covers: PARA Second Brain · What's New in v2.0 · What This Does · How This Differs from Other Second Brain Skills · Quick Setup · 1. Create Directory Structure · 2. Make Notes Searchable (The Symlink Trick) · 3. Enable Session Transcript Indexing · 4. Initialize MEMORY.md · MEMORY.md — Long-Term Memory · About [Human's Name] · Active Context
Findings
MEDIUM Transitive Trust Abuse via Symlink-Based Search Expansion Prompt Injectionllm
The skill instructs users to create a symlink from 'memory/notes' to '../notes' to make the entire notes/ directory searchable via memory_search. This creates transitive trust where the agent will follow and trust content from any file in notes/ (projects, areas, resources, archive) as if it were curated memory. If an attacker places malicious instructions in notes/projects/malicious.md, the agent will find and potentially follow them during memory_search operations. The skill explicitly states 'Your entire notes/ folder is invisible to search' before the symlink, then makes it visible, expanding the attack surface for indirect prompt injection.
SKILL.md
'By default, memory_search only indexes MEMORY.md and memory/*.md. Your entire notes/ folder is inv[isible]' followed by instructions to create symlink 'ln -s ../notes memory/notes' to make all notes searchableWhat is in the package
| File | Kind | Size |
|---|---|---|
SKILL.md | doc | 13 KB |
manifest.json | config | 598 B |
skill.json | config | 282 B |
scripts/setup.sh | script | 2.0 KB |
templates/concept.md | doc | 396 B |
templates/pattern.md | doc | 391 B |
templates/tool.md | doc | 629 B |
External hosts referenced
clawdhub.com fortelabs.com github.com
Hostnames that appear in the skill's files. Referencing a host is not a finding; compare against the findings above and the skill's stated purpose.
Environment variables referenced
WORKSPACE
Package contents recorded 2026-10-22. The scan above ran against the version current at scan time; the two can differ if the skill has since been updated.
What we checked
- Static analyzer. Pattern rules over SKILL.md and bundled files: known-bad commands, exfiltration URLs, secrets, obfuscation.
- Behavioral analyzer. Checks what the skill asks the agent to do against what its description claims it does.
- Llm analyzer. A language model reads the skill and reports intent-level issues the rules cannot express.
- Trigger analyzer. Looks for instructions that fire on conditions the user did not ask for.
- Meta analyzer. A second model pass that validates, deduplicates and re-scores the other analyzers' findings.
What we did not check
- Runtime behaviour. The skill was not executed; findings come from reading its files.
- Anything fetched at install or run time, including remote scripts, package dependencies, and URLs the skill tells the agent to open.
- Content the analyzers cannot read: images, binaries, and some non-English text.
- Known scanner bypass classes. See the methodology and limitations page.
Sources
- Repository: https://clawhub.ai/skills/para-second-brain
- Raw scan result: para-second-brain-scan.json
- Badge for your README:
- Request a re-scan