skills/vm0-ai/vm0-skills/strava/Gen Agent Trust Hub

strava

Pass

Audited by Gen Agent Trust Hub on Mar 18, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes curl and jq commands via bash -c. This is implemented as a workaround to ensure environment variables are correctly handled during command piping in the agent's execution environment (SKILL.md).
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8) due to the ingestion of untrusted data from the Strava API, including activity names, descriptions, and comments (SKILL.md). There are no explicit boundary markers or sanitization procedures described to prevent the agent from potentially following instructions embedded within this external data. The skill's capabilities include performing network requests via curl, as well as reading and writing local files for activity uploads and updates (SKILL.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 18, 2026, 07:15 AM