seo-flow
Warn
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill defines a
/seo flow synccommand inSKILL.mdthat executes a local Python script (python scripts/sync_flow.py). This script is designed to perform updates to the skill's reference files. - [EXTERNAL_DOWNLOADS]: The orchestration logic in
SKILL.mdspecifies that the synchronization process pulls content from an external repository located atgithub.com/AgriciDaniel/flow. The skill also references multiple external SEO and marketing resources inreferences/bibliography.md. - [DYNAMIC_EXECUTION]: The skill uses sub-process invocation to run the
sync_flow.pyscript. Although intended for framework updates, this mechanism executes code at runtime based on external repository content. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external data via user-provided URLs and topics.
- Ingestion points: Commands such as
/seo flow find [url],/seo flow leverage [url], and/seo flow optimize [url]inSKILL.mdtake external URLs as input. - Boundary markers: The orchestration logic does not specify the use of clear delimiters or instructions for the agent to ignore embedded commands within the processed URLs.
- Capability inventory: The skill has the capability to read local files, execute shell commands via Python scripts, and perform network operations during sync.
- Sanitization: There is no evidence of input validation or sanitization for the content retrieved from external URLs before it is processed by the AI prompts.
Audit Metadata