Skip to main content

content-security-scan

Automates a 7-step security scan for external content, ensuring safety against supply-chain attacks and prompt injections.

Install this skill

or
52/100

Security score

The content-security-scan skill was audited on Mar 2, 2026 and we found 8 security issues across 4 threat categories, including 1 critical. Review the findings below before installing.

Categories Tested

Security Issues

medium line 283

Template literal with variable interpolation in command context

SourceSKILL.md
283args: `"${fetchedContent}" "${sourceUrl}"`,
medium line 56

Access to .env file

SourceSKILL.md
56- EXFILTRATION SCAN: Detect curl/wget/fetch to non-github.com domains, process.env access, readFile + HTTP combos
medium line 173

Access to .env file

SourceSKILL.md
173| Outbound HTTP with local data | `fetch`/`curl`/`wget` + `readFile`/`process.env` in same context |
medium line 175

Access to .env file

SourceSKILL.md
175| process.env access | `process.env.` in non-example context |
low line 181

Access to .env file

SourceSKILL.md
181reason: Exfiltrate local secrets, .env files, agent context to attacker server
critical line 154

Prompt injection: ignore instructions

SourceSKILL.md
154| Instruction override | "ignore previous instructions", "disregard all rules", "forget your constraints" |
low line 304

External URL reference

SourceSKILL.md
304--source-url "https://..." \
low line 313

External URL reference

SourceSKILL.md
313"source_url": "https://...",
Scanned on Mar 2, 2026
View Security Dashboard