strava
Pass
Audited by Gen Agent Trust Hub on Apr 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection by ingesting untrusted data from the Strava API.
- Ingestion points: Activity comments, descriptions, and names retrieved from the Strava API (SKILL.md).
- Boundary markers: Absent; the skill does not use delimiters or warnings to separate external data from system instructions.
- Capability inventory: Executes shell commands via curl and writes temporary request data to /tmp/strava_request.json (SKILL.md).
- Sanitization: None; the retrieved content is processed using jq for filtering but is not sanitized to prevent the execution of embedded instructions.
Audit Metadata