launch-strategy
Verdict safe, but 2 findings (2 medium), mainly prompt injection, unauthorized tool use. Most recent scan 2026-02-01.
The 'launch-strategy' skill presents MEDIUM security risks primarily related to transitive trust abuse and incomplete dependencies. The skill directs the agent to automatically read and trust content from an external file ('.claude/product-marketing-context.md') without validation, creating a vector for indirect prompt injection. Additionally, the skill references a missing 'content.py' file that could be exploited through tool shadowing if an attacker places a malicious file with that name in the execution context. The skill lacks optional metadata fields that would improve transparency. The core instruction content appears benign and focused on legitimate product launch strategy guidance. No data exfiltration, credential theft, or command injection patterns were detected. Remediation should focus on removing external file trust dependencies and ensuring all referenced files are bundled with the skill package.
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
When the user wants to plan a product launch, feature announcement, or release strategy. Also use when the user mentions 'launch,' 'Product Hunt,' 'feature release,' 'announcement,' 'go-to-market,' 'beta launch,' 'early access,' 'waitlist,' or 'product update.' This skill covers phased launches, channel strategy, and ongoing launch momentum.
- Package
- 1 file, 12 KB
- SKILL.md
- 1800 words, 12+ sections
- Code
- None. Instructions only.
- Version
- 1.0.0
SKILL.md covers: Launch Strategy · Before Starting · Core Philosophy · The ORB Framework · Owned Channels · Rented Channels · Borrowed Channels · Five-Phase Launch Approach · Phase 1: Internal Launch · Phase 2: Alpha Launch · Phase 3: Beta Launch · Phase 4: Early Access Launch
Findings
MEDIUM Transitive Trust Abuse - External Context File Dependency Prompt Injectionllm
The skill instructions direct the agent to read and trust content from '.claude/product-marketing-context.md' without validation. This file is external to the skill package and could contain malicious instructions that override the skill's intended behavior. The instruction 'read it before asking questions. Use that context' creates a transitive trust relationship where the agent will follow instructions from an untrusted external source.
SKILL.md
Check for product marketing context first: If `.claude/product-marketing-context.md` exists, read it before asking questions. Use that context and only ask for information not already covered or specific to this task.MEDIUM Missing Referenced Script File - Broken Tool Dependency Unauthorized Tool Usellm
The skill references 'content.py' in its instructions but this file is not included in the skill package. This creates an incomplete tool chain where the skill may attempt to use functionality that doesn't exist, potentially causing the agent to improvise behavior or fail unexpectedly. This could be exploited if an attacker places a malicious 'content.py' file in the execution context.
SKILL.md
Files referenced in instructions: content.py
**Referenced File: content.py** (not found)What is in the package
| File | Kind | Size |
|---|---|---|
SKILL.md | doc | 12 KB |
Package contents recorded 2026-10-22 at commit a04cb61a577a. 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://github.com/coreyhaines31/marketingskills
- Raw scan result: launch-strategy-scan.json
- Badge for your README:
- Request a re-scan