semgrep-rule-creator
Pass
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection (LOW): The skill possesses an attack surface for indirect prompt injection due to its use of WebFetch to ingest external documentation.
- Ingestion points: The
Documentationsection inSKILL.mdrequires the agent to fetch content from several external URLs (semgrep.dev, github.com, appsec.guide). - Boundary markers: There are no explicit instructions to the agent to treat the fetched content as untrusted or to ignore embedded instructions within that content.
- Capability inventory: The skill uses
Bash,Write, andEdittools, allowing it to execute arbitrary commands and modify the local filesystem. - Sanitization: No explicit sanitization or validation of the web content is performed before it is used to influence rule generation.
- Command Execution (SAFE): The skill uses the Bash tool to run legitimate Semgrep commands (
semgrep --test,semgrep --dump-ast). These are necessary for the skill's primary function of validating static analysis rules. - External Downloads (SAFE): The skill fetches documentation from trusted sources (semgrep.dev, github.com). Per [TRUST-SCOPE-RULE], these references are considered low risk as they are targeted at well-known documentation repositories.
Audit Metadata