specstory-project-stats

Pass

Audited by Gen Agent Trust Hub on Oct 6, 2026

Risk Level: SAFEDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill transmits a project identifier (either a hash of the repository/folder name or a specific ID from a local configuration file) to SpecStory's cloud platform to fetch metrics. This is the primary intended function of the skill.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection because it retrieves and processes external content from the SpecStory Cloud API, such as session titles and activity summaries, which could be manipulated by an attacker to include hidden instructions.
  • Ingestion points: The fetchStats function in scripts/get-stats.js retrieves JSON-formatted data from the SpecStory Cloud API.
  • Boundary markers: The SKILL.md instructions do not define specific delimiters or instructions for the agent to ignore potentially malicious content within the fetched data.
  • Capability inventory: The skill uses Bash(node *) to run a local script that performs file reading and network requests.
  • Sanitization: The script parses the API's JSON response but does not perform content-based sanitization or filtering of the retrieved strings.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 6, 2026, 04:22 PM