jira-requirement-analyzer
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches external data from a user-configured JIRA instance using the
scripts/fetch_jira.shscript. This is required for the skill's primary function of requirement analysis. - [COMMAND_EXECUTION]: The skill executes a local shell script (
scripts/fetch_jira.sh) that utilizes standard system tools likecurlandjqto communicate with the JIRA API. The script correctly uses double quotes for variables to mitigate common shell injection risks. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from external JIRA tickets, which presents an inherent surface for indirect prompt injection.
- Ingestion points: Data enters the context via the
scripts/fetch_jira.shscript which pulls summaries, descriptions, and acceptance criteria from JIRA issues. - Boundary markers: The skill implements a mandatory "HUMAN REVIEW GATE" and uses "Anti Hallucination STRICT RULES" to ensure all assertions are traceable and reviewed by a user before any output is finalized.
- Capability inventory: The skill can perform network requests (
curl) and write temporary HTML files to the/tmpdirectory. - Sanitization: The skill relies on instructional guardrails and human oversight to identify and ignore potential malicious instructions embedded within ticket content.
- [DATA_EXPOSURE_AND_EXFILTRATION]: The skill accesses sensitive credentials (
JIRA_EMAIL,JIRA_TOKEN) via environment variables rather than hardcoding them. This aligns with standard security practices for credential management in automated tools.
Audit Metadata