Verdict safe, but 2 findings (2 medium), mainly data exfiltration, unauthorized tool use. Most recent scan 2026-02-06.
The Instagram skill presents MEDIUM security risks primarily due to missing implementation details despite broad capability claims, and inadequate security guidance for access token handling. The skill requires a sensitive Instagram access token with potentially broad permissions but provides no security warnings or best practices. Most critically, the skill claims extensive functionality (posting, analytics, comment management) but contains no actual implementation code, creating a tool exploitation risk where unrestricted bash/curl commands may be used with the access token. The missing metadata fields (license, compatibility, allowed-tools) reduce transparency about the skill's intended behavior and restrictions. While no active malicious code was detected, the combination of sensitive credential requirements, missing implementation, and lack of security guidance creates meaningful risk. The skill requires significant hardening before production use.
Scanner's overall assessment (LLM analyzer)
Second scanner: NVIDIA SkillSpector
Independent static run, no language model, over the same files as the Cisco scan above. How the two scanners compare across the whole corpus: Two scanners, one corpus.
What this skill does
Instagram platform integration. Post content, manage stories, view insights, and engage with followers.
- Package
- 1 file, 626 B
- SKILL.md
- 48 words, 4 sections
- Code
- None. Instructions only.
- Requires
- bins:
curljq
SKILL.md covers: Instagram 📸 · Setup · Features · Usage Examples
Findings
MEDIUM Hardcoded Access Token in Documentation Data Exfiltrationllm
The skill documentation instructs users to export INSTAGRAM_ACCESS_TOKEN as an environment variable. While this is a common pattern, the documentation does not provide any warnings about token security, rotation policies, or scope limitations. Instagram access tokens can provide broad access to user accounts including posting content, accessing private messages, and viewing analytics. The skill's metadata indicates this token is required (primaryEnv: INSTAGRAM_ACCESS_TOKEN) but lacks security guidance.
SKILL.md:9
```bash
export INSTAGRAM_ACCESS_TOKEN="your_access_token"
```MEDIUM Missing Implementation with Broad Capability Claims Unauthorized Tool Usellm
The skill claims to provide extensive Instagram functionality (post content, manage stories, view insights, engage with followers, comment management, follower analytics, hashtag research) but contains no script files or implementation code. This creates a tool shadowing risk where the agent may attempt to fulfill these capabilities using unrestricted bash/curl commands with the access token, potentially leading to unvalidated API calls, improper error handling, or unsafe data processing. The metadata indicates required binaries (curl, jq) suggesting shell-based implementation is expected.
SKILL.md:1
Claimed features: Post photos/videos, Manage stories, View insights, Comment management, Follower analytics, Hashtag research. Actual implementation: No script files found. Required binaries: curl, jq.What is in the package
| File | Kind | Size |
|---|---|---|
SKILL.md | doc | 626 B |
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/instagram
- Raw scan result: instagram-scan.json
- Badge for your README:
- Request a re-scan